## Warning in reticulate::use_condaenv(settings$val, required = TRUE): multiple Conda environments found; the first-listed will be chosen.
##              name                                                                      python
## 5  spacy_condaenv /home/redapemusic35/.local/share/r-miniconda/envs/spacy_condaenv/bin/python
## 11 spacy_condaenv               /home/redapemusic35/miniconda3/envs/spacy_condaenv/bin/python

## Warning: Python '/home/redapemusic35/.local/share/r-miniconda/envs/spacy_condaenv/bin/python' was requested but '/home/redapemusic35/miniconda3/bin/
## python3' was loaded instead (see reticulate::py_config() for more information)

##  [1] "I can't wait to show you where I grew up."                                                                                   
##  [2] "Walk you 'round the foothills of my town."                                                                                   
##  [3] "Probably feel like you've been there before,\nAfter hearing all the stories; I've been telling you\nFor six months now."     
##  [4] "We'll probably have to sleep in separate bedrooms."                                                                          
##  [5] "Pack a shirt for church because we'll go."                                                                                   
##  [6] "I'm not trying to scare you off."                                                                                            
##  [7] "But I just thought that we should talk; a few things out,\nBefore we hit the road."                                          
##  [8] "If I bring you home to Mama,\nI guess I better warn ya,\nShe falls in love a little faster than I do."                       
##  [9] "And my dad will check your tires."                                                                                           
## [10] "Pour you whiskey over ice."                                                                                                  
## [11] "And take you fishing but pretend that he don't like you."                                                                    
## [12] "If we break up, I'll be fine."                                                                                               
## [13] "But you'll be breaking more hearts than mine."                                                                               
## [14] "My sister's gonna ask a million questions."                                                                                  
## [15] "Say anything she can to turn you red."                                                                                       
## [16] "And when you meet my high school friends;\nThey'll buy you drinks and fill you in;\nOn all the crazy nights I can't outlive."
## [17] "If I bring you home to Mama,\nI guess I better warn ya,\nShe falls in love a little faster than I do."                       
## [18] "And my dad will check your tires."                                                                                           
## [19] "Pour you whiskey over ice."                                                                                                  
## [20] "And take you fishing but pretend that he don't like you."                                                                    
## [21] "If we break up, I'll be fine."                                                                                               
## [22] "But you'll be breaking more hearts than mine."                                                                               
## [23] "If I bring you home to Mama;\nI guess I better warn ya;\nShe feels every heartache I go through."                            
## [24] "And if my dad sees me crying;\nHe'll pour some whiskey over ice;\nAnd tell a lie and say he never really liked you."         
## [25] "If we break up, I'll be fine;\nBut you'll be breaking more hearts than mine."                                                
## [26] "You'll be breaking more hearts than mine."

First we are using Tyler Rinker’s sentimentr.

##     element_id sentence_id word_count   sentiment
##  1:          1           1         10  0.07905694
##  2:          2           1          8  0.00000000
##  3:          3           1         20  0.11180340
##  4:          4           1          8  0.08838835
##  5:          5           1          8  0.03535534
##  6:          6           1          7  0.28347335
##  7:          7           1         17  0.03638034
##  8:          8           1         23  0.01459601
##  9:          9           1          7  0.00000000
## 10:         10           1          5  0.00000000
## 11:         11           1         11 -0.84800066
## 12:         12           1          7 -0.28347335
## 13:         13           1          8 -0.64700270
## 14:         14           1          7  0.00000000
## 15:         15           1          8  0.00000000
## 16:         16           1         24 -0.10206207
## 17:         17           1         23  0.01459601
## 18:         18           1          7  0.00000000
## 19:         19           1          5  0.00000000
## 20:         20           1         11 -0.84800066
## 21:         21           1          7 -0.28347335
## 22:         22           1          8 -0.64700270
## 23:         23           1         20 -0.21242646
## 24:         24           1         24 -0.22453656
## 25:         25           1         15 -0.66615314
## 26:         26           1          7 -0.40820163
##     element_id sentence_id word_count   sentiment

Now we will use Taylor Arnold’s coreNLP Stanford wrapper.

##    id sentimentValue sentiment
## 1   1              1  Negative
## 2   2              3  Positive
## 3   3              1  Negative
## 4   4              1  Negative
## 5   5              1  Negative
## 6   6              1  Negative
## 7   7              3  Positive
## 8   8              1  Negative
## 9   9              1  Negative
## 10 10              2   Neutral
## 11 11              1  Negative
## 12 12              3  Positive
## 13 13              3  Positive
## 14 14              2   Neutral
## 15 15              3  Positive
## 16 16              1  Negative
## 17 17              1  Negative
## 18 18              1  Negative
## 19 19              2   Neutral
## 20 20              1  Negative
## 21 21              3  Positive
## 22 22              3  Positive
## 23 23              1  Negative
## 24 24              1  Negative
## 25 25              3  Positive
## 26 26              2   Neutral

Sentiment analysis weights expressed emotions ((f)) on a scale between -1 and 1, (- / +). Above 0 equates to positive feelings while below 0 equates to negative ones.

Axis of
Emotion

With this understanding, you might be able to tell visually, that sentimentr appears more accurate than the stanford wrapper. For instance, Sentimentr scores sentence #1 I can\'t wait to show you where I grew up. 0.07905694. Anything above 0 is a positive score, at the same time however, coreNLP scores #1 negative, which would be less than 0. But #1 at the very least seems to express some modicum of excitement, though given the context of the song we might say only with a little bit of trepidation.[1]

But according to Rinker’s own admission:

He also utilizes a wrapper for the Stanford coreNLP which uses much more sophisticated analysis. Jocker’s dictionary methods are fast but are more prone to error in the case of valence shifters. Jocker’s addressed these critiques explaining that the method is good with regard to analyzing general sentiment in a piece of literature. He points to the accuracy of the Stanford detection as well. In my own work I need better accuracy than a simple dictionary lookup; something that considers valence shifters yet optimizes speed which the Stanford’s parser does not. This leads to a trade off of speed vs. accuracy. Simply, sentimentr attempts to balance accuracy and speed.

This should not be. Stanford should be the more accurate model.

As such, we are getting some kind of error. One thing that I could do, is use Stanford’s Java which in the past has given me fairly accurate results. Here they are now:

Document: ID=More-Hearts-1.txt (20 sentences, 370 tokens)

Sentence #1 (12 tokens, sentiment: Negative): I can’t wait to show you where I grew up.

Tokens: [Text=I CharacterOffsetBegin=0 CharacterOffsetEnd=1 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=ca CharacterOffsetBegin=2 CharacterOffsetEnd=4 PartOfSpeech=MD Lemma=can NamedEntityTag=O SentimentClass=Neutral] [Text=n’t CharacterOffsetBegin=4 CharacterOffsetEnd=7 PartOfSpeech=RB Lemma=not NamedEntityTag=O SentimentClass=Neutral] [Text=wait CharacterOffsetBegin=8 CharacterOffsetEnd=12 PartOfSpeech=VB Lemma=wait NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=13 CharacterOffsetEnd=15 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=show CharacterOffsetBegin=16 CharacterOffsetEnd=20 PartOfSpeech=VB Lemma=show NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=21 CharacterOffsetEnd=24 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=where CharacterOffsetBegin=25 CharacterOffsetEnd=30 PartOfSpeech=WRB Lemma=where NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=31 CharacterOffsetEnd=32 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=grew CharacterOffsetBegin=33 CharacterOffsetEnd=37 PartOfSpeech=VBD Lemma=grow NamedEntityTag=O SentimentClass=Neutral] [Text=up CharacterOffsetBegin=38 CharacterOffsetEnd=40 PartOfSpeech=RP Lemma=up NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=40 CharacterOffsetEnd=41 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (NP (PRP I)) (VP (MD ca) (RB n’t) (VP (VB wait) (S (VP (TO to) (VP (VB show) (NP (PRP you)) (SBAR (WHADVP (WRB where)) (S (NP (PRP I)) (VP (VBD grew) (PRT (RP up)))))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.550    
(NP sentiment=2 prob=0.996 I) (@S sentiment=1 prob=0.588
(VP sentiment=1 prob=0.528 (@VP sentiment=2 prob=0.987
(MD sentiment=2 prob=0.998 ca) (RB sentiment=2 prob=0.994 n’t))
(VP sentiment=2 prob=0.348 (VB sentiment=2 prob=0.967 wait)
(S sentiment=2 prob=0.798 (TO sentiment=2 prob=0.990 to)
(VP sentiment=2 prob=0.769 (@VP sentiment=2 prob=0.957
(VB sentiment=2 prob=0.997 show) (NP sentiment=2 prob=0.995 you))
(SBAR sentiment=2 prob=0.903 (WHADVP sentiment=2 prob=0.993 where)
(S sentiment=2 prob=0.885 (NP sentiment=2 prob=0.996 I)
(VP sentiment=2 prob=0.973 (VBD sentiment=2 prob=0.994 grew)
(PRT sentiment=2 prob=0.997 up)))))))) (. sentiment=2 prob=0.997 .)))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, wait-4) nsubj(wait-4, I-1) nsubj:xsubj(show-6, I-1) aux(wait-4, ca-2) neg(wait-4, n’t-3) mark(show-6, to-5) xcomp(wait-4, show-6) dobj(show-6, you-7) advmod(grew-10, where-8) nsubj(grew-10, I-9) advcl(show-6, grew-10) compound:prt(grew-10, up-11) punct(wait-4, .-12)

Extracted the following NER entity mentions:

Sentence #2 (10 tokens, sentiment: Positive): Walk you ’round the foothills of my town.

Tokens: [Text=Walk CharacterOffsetBegin=42 CharacterOffsetEnd=46 PartOfSpeech=VB Lemma=walk NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=47 CharacterOffsetEnd=50 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=’ CharacterOffsetBegin=51 CharacterOffsetEnd=52 PartOfSpeech=’’ Lemma=’ NamedEntityTag=O SentimentClass=Neutral] [Text=round CharacterOffsetBegin=52 CharacterOffsetEnd=57 PartOfSpeech=VBP Lemma=round NamedEntityTag=O SentimentClass=Neutral] [Text=the CharacterOffsetBegin=58 CharacterOffsetEnd=61 PartOfSpeech=DT Lemma=the NamedEntityTag=O SentimentClass=Neutral] [Text=foothills CharacterOffsetBegin=62 CharacterOffsetEnd=71 PartOfSpeech=NNS Lemma=foothill NamedEntityTag=O SentimentClass=Neutral] [Text=of CharacterOffsetBegin=72 CharacterOffsetEnd=74 PartOfSpeech=IN Lemma=of NamedEntityTag=O SentimentClass=Neutral] [Text=my CharacterOffsetBegin=75 CharacterOffsetEnd=77 PartOfSpeech=PRP$ Lemma=my NamedEntityTag=O SentimentClass=Neutral] [Text=town CharacterOffsetBegin=78 CharacterOffsetEnd=82 PartOfSpeech=NN Lemma=town NamedEntityTag=O SentimentClass=Positive] [Text=. CharacterOffsetBegin=82 CharacterOffsetEnd=83 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (VP (VB Walk) (NP (PRP you) (’’ ’)))) (VP (VBP round) (NP (NP (DT the) (NNS foothills)) (PP (IN of) (NP (PRP$ my) (NN town))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=3 prob=0.698    
(S sentiment=3 prob=0.583 (VB sentiment=2 prob=0.841 Walk)
(NP sentiment=2 prob=0.950 (PRP sentiment=2 prob=0.995 you)
(’‘ sentiment=2 prob=0.998’))) (@S sentiment=2 prob=0.656
(VP sentiment=2 prob=0.819 (VBP sentiment=2 prob=0.957 round)
(NP sentiment=2 prob=0.440 (NP sentiment=2 prob=0.846
(DT sentiment=2 prob=0.994 the) (NNS sentiment=2 prob=0.631 foothills))
(PP sentiment=3 prob=0.520 (IN sentiment=2 prob=0.993 of)
(NP sentiment=2 prob=0.925 (PRP$ sentiment=2 prob=0.998 my)
(NN sentiment=3 prob=0.879 town))))) (. sentiment=2 prob=0.997 .)))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, round-4) csubj(round-4, Walk-1) dobj(Walk-1, you-2) punct(you-2, ’-3) det(foothills-6, the-5) dobj(round-4, foothills-6) case(town-9, of-7) nmod:poss(town-9, my-8) nmod:of(foothills-6, town-9) punct(round-4, .-10)

Extracted the following NER entity mentions:

Sentence #3 (25 tokens, sentiment: Negative): Probably feel like you’ve been there before, After hearing all the stories; I’ve been telling you For six months now.

Tokens: [Text=Probably CharacterOffsetBegin=84 CharacterOffsetEnd=92 PartOfSpeech=RB Lemma=probably NamedEntityTag=O SentimentClass=Neutral] [Text=feel CharacterOffsetBegin=93 CharacterOffsetEnd=97 PartOfSpeech=VB Lemma=feel NamedEntityTag=O SentimentClass=Neutral] [Text=like CharacterOffsetBegin=98 CharacterOffsetEnd=102 PartOfSpeech=IN Lemma=like NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=103 CharacterOffsetEnd=106 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=’ve CharacterOffsetBegin=106 CharacterOffsetEnd=109 PartOfSpeech=VBP Lemma=have NamedEntityTag=O SentimentClass=Neutral] [Text=been CharacterOffsetBegin=110 CharacterOffsetEnd=114 PartOfSpeech=VBN Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=there CharacterOffsetBegin=115 CharacterOffsetEnd=120 PartOfSpeech=RB Lemma=there NamedEntityTag=O SentimentClass=Neutral] [Text=before CharacterOffsetBegin=121 CharacterOffsetEnd=127 PartOfSpeech=RB Lemma=before NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=127 CharacterOffsetEnd=128 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=After CharacterOffsetBegin=129 CharacterOffsetEnd=134 PartOfSpeech=IN Lemma=after NamedEntityTag=O SentimentClass=Neutral] [Text=hearing CharacterOffsetBegin=135 CharacterOffsetEnd=142 PartOfSpeech=VBG Lemma=hear NamedEntityTag=O SentimentClass=Neutral] [Text=all CharacterOffsetBegin=143 CharacterOffsetEnd=146 PartOfSpeech=PDT Lemma=all NamedEntityTag=O SentimentClass=Neutral] [Text=the CharacterOffsetBegin=147 CharacterOffsetEnd=150 PartOfSpeech=DT Lemma=the NamedEntityTag=O SentimentClass=Neutral] [Text=stories CharacterOffsetBegin=151 CharacterOffsetEnd=158 PartOfSpeech=NNS Lemma=story NamedEntityTag=O SentimentClass=Neutral] [Text=; CharacterOffsetBegin=158 CharacterOffsetEnd=159 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=160 CharacterOffsetEnd=161 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=’ve CharacterOffsetBegin=161 CharacterOffsetEnd=164 PartOfSpeech=VBP Lemma=have NamedEntityTag=O SentimentClass=Neutral] [Text=been CharacterOffsetBegin=165 CharacterOffsetEnd=169 PartOfSpeech=VBN Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=telling CharacterOffsetBegin=170 CharacterOffsetEnd=177 PartOfSpeech=VBG Lemma=tell NamedEntityTag=O SentimentClass=Positive] [Text=you CharacterOffsetBegin=178 CharacterOffsetEnd=181 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=For CharacterOffsetBegin=182 CharacterOffsetEnd=185 PartOfSpeech=IN Lemma=for NamedEntityTag=O SentimentClass=Neutral] [Text=six CharacterOffsetBegin=186 CharacterOffsetEnd=189 PartOfSpeech=CD Lemma=six NamedEntityTag=DURATION NormalizedNamedEntityTag=P6M Timex=six months SentimentClass=Neutral] [Text=months CharacterOffsetBegin=190 CharacterOffsetEnd=196 PartOfSpeech=NNS Lemma=month NamedEntityTag=DURATION NormalizedNamedEntityTag=P6M Timex=six months SentimentClass=Neutral] [Text=now CharacterOffsetBegin=197 CharacterOffsetEnd=200 PartOfSpeech=RB Lemma=now NamedEntityTag=DATE NormalizedNamedEntityTag=PRESENT_REF Timex=now SentimentClass=Neutral] [Text=. CharacterOffsetBegin=200 CharacterOffsetEnd=201 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (ADVP (RB Probably)) (VP (VB feel) (SBAR (IN like) (S (NP (PRP you)) (VP (VBP ’ve) (VP (VBN been) (ADVP (RB there)) (ADVP (RB before)))) (, ,) (PP (IN After) (S (VP (VBG hearing) (NP (PDT all) (DT the) (NNS stories))))))))) (: ;) (S (NP (PRP I)) (VP (VBP ’ve) (VP (VBN been) (VP (VBG telling) (S (NP (PRP you)) (PP (IN For) (NP (CD six) (NNS months)))) (ADVP (RB now)))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.510    
(@S sentiment=1 prob=0.538 (@S sentiment=1 prob=0.488
(S sentiment=1 prob=0.447 (ADVP sentiment=2 prob=0.864 Probably)
(VP sentiment=1 prob=0.488 (VB sentiment=2 prob=0.990 feel)
(SBAR sentiment=1 prob=0.527 (IN sentiment=2 prob=0.995 like)
(S sentiment=2 prob=0.400 (NP sentiment=2 prob=0.995 you)
(@S sentiment=1 prob=0.395 (@S sentiment=2 prob=0.548
(VP sentiment=2 prob=0.792 (VBP sentiment=2 prob=0.996 ’ve)
(VP sentiment=2 prob=0.893 (@VP sentiment=2 prob=0.961
(VBN sentiment=2 prob=0.992 been) (ADVP sentiment=2 prob=0.996 there))
(ADVP sentiment=2 prob=0.993 before))) (, sentiment=2 prob=0.997 ,))
(PP sentiment=3 prob=0.672 (IN sentiment=2 prob=0.997 After)
(S sentiment=2 prob=0.536 (VBG sentiment=2 prob=0.884 hearing)
(NP sentiment=2 prob=0.920 (PDT sentiment=2 prob=0.995 all)
(@NP sentiment=2 prob=0.961 (DT sentiment=2 prob=0.994 the)
(NNS sentiment=2 prob=0.997 stories)))))))))) (: sentiment=2 prob=0.997
;)) (S sentiment=2 prob=0.852 (NP sentiment=2 prob=0.996 I)
(VP sentiment=2 prob=0.958 (VBP sentiment=2 prob=0.996 ’ve)
(VP sentiment=2 prob=0.917 (VBN sentiment=2 prob=0.992 been)
(VP sentiment=2 prob=0.965 (@VP sentiment=2 prob=0.921
(VBG sentiment=3 prob=0.945 telling) (S sentiment=2 prob=0.937
(NP sentiment=2 prob=0.995 you) (PP sentiment=2 prob=0.957
(IN sentiment=2 prob=0.997 For) (NP sentiment=2 prob=0.956
(CD sentiment=2 prob=0.969 six) (NNS sentiment=2 prob=0.980 months)))))
(ADVP sentiment=2 prob=0.998 now)))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, feel-2) advmod(feel-2, Probably-1) mark(been-6, like-3) nsubj(been-6, you-4) aux(been-6, ’ve-5) advcl:like(feel-2, been-6) advmod(been-6, there-7) advmod(been-6, before-8) punct(been-6, ,-9) mark(hearing-11, After-10) advcl:after(been-6, hearing-11) det:predet(stories-14, all-12) det(stories-14, the-13) dobj(hearing-11, stories-14) punct(feel-2, ;-15) nsubj(telling-19, I-16) aux(telling-19, ’ve-17) aux(telling-19, been-18) parataxis(feel-2, telling-19) xcomp(telling-19, you-20) case(months-23, For-21) nummod(months-23, six-22) dep(you-20, months-23) advmod(telling-19, now-24) punct(feel-2, .-25)

Extracted the following NER entity mentions: six months DURATION now DATE

Sentence #4 (10 tokens, sentiment: Negative): We’ll probably have to sleep in separate bedrooms.

Tokens: [Text=We CharacterOffsetBegin=203 CharacterOffsetEnd=205 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=205 CharacterOffsetEnd=208 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=probably CharacterOffsetBegin=209 CharacterOffsetEnd=217 PartOfSpeech=RB Lemma=probably NamedEntityTag=O SentimentClass=Neutral] [Text=have CharacterOffsetBegin=218 CharacterOffsetEnd=222 PartOfSpeech=VB Lemma=have NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=223 CharacterOffsetEnd=225 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=sleep CharacterOffsetBegin=226 CharacterOffsetEnd=231 PartOfSpeech=VB Lemma=sleep NamedEntityTag=O SentimentClass=Negative] [Text=in CharacterOffsetBegin=232 CharacterOffsetEnd=234 PartOfSpeech=IN Lemma=in NamedEntityTag=O SentimentClass=Neutral] [Text=separate CharacterOffsetBegin=235 CharacterOffsetEnd=243 PartOfSpeech=JJ Lemma=separate NamedEntityTag=O SentimentClass=Neutral] [Text=bedrooms CharacterOffsetBegin=244 CharacterOffsetEnd=252 PartOfSpeech=NNS Lemma=bedroom NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=252 CharacterOffsetEnd=253 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (NP (PRP We)) (VP (MD ’ll) (ADVP (RB probably)) (VP (VB have) (S (VP (TO to) (VP (VB sleep) (PP (IN in) (NP (JJ separate) (NNS bedrooms)))))))) (. .)))

Sentiment-annotated binary tree: (ROOT|sentiment=1|prob=0.708 (NP|sentiment=2|prob=0.992 We) (@S|sentiment=1|prob=0.484 (VP|sentiment=2|prob=0.488 (@VP|sentiment=2|prob=0.685 (MD|sentiment=2|prob=0.998 ’ll) (ADVP|sentiment=2|prob=0.994 probably)) (VP|sentiment=2|prob=0.637 (VB|sentiment=2|prob=0.991 have) (S|sentiment=2|prob=0.677 (TO|sentiment=2|prob=0.990 to) (VP|sentiment=2|prob=0.680 (VB|sentiment=1|prob=0.788 sleep) (PP|sentiment=2|prob=0.923 (IN|sentiment=2|prob=0.993 in) (NP|sentiment=2|prob=0.871 (JJ|sentiment=2|prob=0.955 separate) (NNS|sentiment=2|prob=0.631 bedrooms))))))) (.|sentiment=2|prob=0.997 .)))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, have-4) nsubj(have-4, We-1) nsubj:xsubj(sleep-6, We-1) aux(have-4, ’ll-2) advmod(have-4, probably-3) mark(sleep-6, to-5) xcomp(have-4, sleep-6) case(bedrooms-9, in-7) amod(bedrooms-9, separate-8) nmod:in(sleep-6, bedrooms-9) punct(have-4, .-10)

Extracted the following NER entity mentions:

Sentence #5 (10 tokens, sentiment: Negative): Pack a shirt for church because we’ll go.

Tokens: [Text=Pack CharacterOffsetBegin=254 CharacterOffsetEnd=258 PartOfSpeech=VB Lemma=pack NamedEntityTag=O SentimentClass=Neutral] [Text=a CharacterOffsetBegin=259 CharacterOffsetEnd=260 PartOfSpeech=DT Lemma=a NamedEntityTag=O SentimentClass=Neutral] [Text=shirt CharacterOffsetBegin=261 CharacterOffsetEnd=266 PartOfSpeech=NN Lemma=shirt NamedEntityTag=O SentimentClass=Neutral] [Text=for CharacterOffsetBegin=267 CharacterOffsetEnd=270 PartOfSpeech=IN Lemma=for NamedEntityTag=O SentimentClass=Neutral] [Text=church CharacterOffsetBegin=271 CharacterOffsetEnd=277 PartOfSpeech=NN Lemma=church NamedEntityTag=O SentimentClass=Neutral] [Text=because CharacterOffsetBegin=278 CharacterOffsetEnd=285 PartOfSpeech=IN Lemma=because NamedEntityTag=O SentimentClass=Neutral] [Text=we CharacterOffsetBegin=286 CharacterOffsetEnd=288 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=288 CharacterOffsetEnd=291 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=go CharacterOffsetBegin=292 CharacterOffsetEnd=294 PartOfSpeech=VB Lemma=go NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=294 CharacterOffsetEnd=295 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (VP (VB Pack) (NP (NP (DT a) (NN shirt)) (PP (IN for) (NP (NN church)))) (SBAR (IN because) (S (NP (PRP we)) (VP (MD ’ll) (VP (VB go)))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.647    
(VP sentiment=1 prob=0.625 (@VP sentiment=1 prob=0.455
(VB sentiment=2 prob=0.631 Pack) (NP sentiment=1 prob=0.434
(NP sentiment=2 prob=0.560 (DT sentiment=2 prob=0.990 a)
(NN sentiment=2 prob=0.816 shirt)) (PP sentiment=2 prob=0.830
(IN sentiment=2 prob=0.992 for) (NP sentiment=2 prob=0.936 church))))
(SBAR sentiment=2 prob=0.870 (IN sentiment=2 prob=0.999 because)
(S sentiment=2 prob=0.839 (NP sentiment=2 prob=0.996 we)
(VP sentiment=2 prob=0.976 (MD sentiment=2 prob=0.998 ’ll)
(VP sentiment=2 prob=0.997 go))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, Pack-1) det(shirt-3, a-2) dobj(Pack-1, shirt-3) case(church-5, for-4) nmod:for(shirt-3, church-5) mark(go-9, because-6) nsubj(go-9, we-7) aux(go-9, ’ll-8) advcl:because(Pack-1, go-9) punct(Pack-1, .-10)

Extracted the following NER entity mentions:

Sentence #6 (9 tokens, sentiment: Negative): I’m not trying to scare you off.

Tokens: [Text=I CharacterOffsetBegin=296 CharacterOffsetEnd=297 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=’m CharacterOffsetBegin=297 CharacterOffsetEnd=299 PartOfSpeech=VBP Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=not CharacterOffsetBegin=300 CharacterOffsetEnd=303 PartOfSpeech=RB Lemma=not NamedEntityTag=O SentimentClass=Negative] [Text=trying CharacterOffsetBegin=304 CharacterOffsetEnd=310 PartOfSpeech=VBG Lemma=try NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=311 CharacterOffsetEnd=313 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=scare CharacterOffsetBegin=314 CharacterOffsetEnd=319 PartOfSpeech=VB Lemma=scare NamedEntityTag=O SentimentClass=Negative] [Text=you CharacterOffsetBegin=320 CharacterOffsetEnd=323 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=off CharacterOffsetBegin=324 CharacterOffsetEnd=327 PartOfSpeech=RP Lemma=off NamedEntityTag=O SentimentClass=Negative] [Text=. CharacterOffsetBegin=327 CharacterOffsetEnd=328 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (NP (PRP I)) (VP (VBP ’m) (RB not) (VP (VBG trying) (S (VP (TO to) (VP (VB scare) (NP (PRP you)) (PRT (RP off))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.648    
(NP sentiment=2 prob=0.996 I) (@S sentiment=1 prob=0.609
(VP sentiment=1 prob=0.519 (@VP sentiment=2 prob=0.554
(VBP sentiment=2 prob=0.934 ’m) (RB sentiment=1 prob=0.974 not))
(VP sentiment=1 prob=0.668 (VBG sentiment=2 prob=0.991 trying)
(S sentiment=1 prob=0.353 (TO sentiment=2 prob=0.990 to)
(VP sentiment=1 prob=0.306 (@VP sentiment=2 prob=0.493
(VB sentiment=1 prob=0.422 scare) (NP sentiment=2 prob=0.995 you))
(PRT sentiment=1 prob=0.950 off))))) (. sentiment=2 prob=0.997 .)))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, trying-4) nsubj(trying-4, I-1) nsubj:xsubj(scare-6, I-1) aux(trying-4, ’m-2) neg(trying-4, not-3) mark(scare-6, to-5) xcomp(trying-4, scare-6) dobj(scare-6, you-7) compound:prt(scare-6, off-8) punct(trying-4, .-9)

Extracted the following NER entity mentions:

Sentence #7 (19 tokens, sentiment: Positive): But I just thought that we should talk; a few things out Before we hit the road.

Tokens: [Text=But CharacterOffsetBegin=330 CharacterOffsetEnd=333 PartOfSpeech=CC Lemma=but NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=334 CharacterOffsetEnd=335 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=just CharacterOffsetBegin=336 CharacterOffsetEnd=340 PartOfSpeech=RB Lemma=just NamedEntityTag=O SentimentClass=Neutral] [Text=thought CharacterOffsetBegin=341 CharacterOffsetEnd=348 PartOfSpeech=VBD Lemma=think NamedEntityTag=O SentimentClass=Neutral] [Text=that CharacterOffsetBegin=349 CharacterOffsetEnd=353 PartOfSpeech=IN Lemma=that NamedEntityTag=O SentimentClass=Neutral] [Text=we CharacterOffsetBegin=354 CharacterOffsetEnd=356 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=should CharacterOffsetBegin=357 CharacterOffsetEnd=363 PartOfSpeech=MD Lemma=should NamedEntityTag=O SentimentClass=Neutral] [Text=talk CharacterOffsetBegin=364 CharacterOffsetEnd=368 PartOfSpeech=VB Lemma=talk NamedEntityTag=O SentimentClass=Neutral] [Text=; CharacterOffsetBegin=368 CharacterOffsetEnd=369 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=a CharacterOffsetBegin=370 CharacterOffsetEnd=371 PartOfSpeech=DT Lemma=a NamedEntityTag=O SentimentClass=Neutral] [Text=few CharacterOffsetBegin=372 CharacterOffsetEnd=375 PartOfSpeech=JJ Lemma=few NamedEntityTag=O SentimentClass=Neutral] [Text=things CharacterOffsetBegin=376 CharacterOffsetEnd=382 PartOfSpeech=NNS Lemma=thing NamedEntityTag=O SentimentClass=Neutral] [Text=out CharacterOffsetBegin=383 CharacterOffsetEnd=386 PartOfSpeech=RP Lemma=out NamedEntityTag=O SentimentClass=Negative] [Text=Before CharacterOffsetBegin=387 CharacterOffsetEnd=393 PartOfSpeech=IN Lemma=before NamedEntityTag=O SentimentClass=Neutral] [Text=we CharacterOffsetBegin=394 CharacterOffsetEnd=396 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=hit CharacterOffsetBegin=397 CharacterOffsetEnd=400 PartOfSpeech=VBD Lemma=hit NamedEntityTag=O SentimentClass=Positive] [Text=the CharacterOffsetBegin=401 CharacterOffsetEnd=404 PartOfSpeech=DT Lemma=the NamedEntityTag=O SentimentClass=Neutral] [Text=road CharacterOffsetBegin=405 CharacterOffsetEnd=409 PartOfSpeech=NN Lemma=road NamedEntityTag=O SentimentClass=Negative] [Text=. CharacterOffsetBegin=409 CharacterOffsetEnd=410 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (CC But) (NP (PRP I)) (ADVP (RB just)) (VP (VBD thought) (SBAR (IN that) (S (NP (PRP we)) (VP (MD should) (VP (VB talk))) (: ;) (SBAR (NP (NP (DT a) (JJ few) (NNS things)) (ADVP (RP out))) (IN Before) (S (NP (PRP we)) (VP (VBD hit) (NP (DT the) (NN road)))))))) (. .)))

Sentiment-annotated binary tree: (ROOT|sentiment=3|prob=0.420 (CC|sentiment=2|prob=0.999 But) (@S|sentiment=3|prob=0.400 (NP|sentiment=2|prob=0.996 I) (@S|sentiment=3|prob=0.400 (ADVP|sentiment=2|prob=0.996 just) (@S|sentiment=3|prob=0.473 (VP|sentiment=2|prob=0.483 (VBD|sentiment=2|prob=0.997 thought) (SBAR|sentiment=2|prob=0.504 (IN|sentiment=2|prob=0.991 that) (S|sentiment=2|prob=0.486 (NP|sentiment=2|prob=0.996 we) (@S|sentiment=2|prob=0.421 (@S|sentiment=2|prob=0.708 (VP|sentiment=2|prob=0.926 (MD|sentiment=2|prob=0.998 should) (VP|sentiment=2|prob=0.984 talk)) (:|sentiment=2|prob=0.997 ;)) (SBAR|sentiment=2|prob=0.502 (NP|sentiment=2|prob=0.911 (NP|sentiment=2|prob=0.951 (DT|sentiment=2|prob=0.990 a) (@NP|sentiment=2|prob=0.928 (JJ|sentiment=2|prob=0.994 few) (NNS|sentiment=2|prob=0.992 things))) (ADVP|sentiment=1|prob=0.945 out)) (@SBAR|sentiment=2|prob=0.840 (IN|sentiment=2|prob=0.988 Before) (S|sentiment=2|prob=0.741 (NP|sentiment=2|prob=0.996 we) (VP|sentiment=2|prob=0.828 (VBD|sentiment=3|prob=0.909 hit) (NP|sentiment=2|prob=0.977 (DT|sentiment=2|prob=0.994 the) (NN|sentiment=1|prob=0.857 road)))))))))) (.|sentiment=2|prob=0.997 .)))))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, thought-4) cc(thought-4, But-1) nsubj(thought-4, I-2) advmod(thought-4, just-3) mark(talk-8, that-5) nsubj(talk-8, we-6) aux(talk-8, should-7) ccomp(thought-4, talk-8) punct(talk-8, ;-9) det(things-12, a-10) amod(things-12, few-11) dep(hit-16, things-12) advmod(things-12, out-13) mark(hit-16, Before-14) nsubj(hit-16, we-15) parataxis(talk-8, hit-16) det(road-18, the-17) dobj(hit-16, road-18) punct(thought-4, .-19)

Extracted the following NER entity mentions:

Sentence #8 (26 tokens, sentiment: Negative): If I bring you home to Mama, I guess I better warn ya, She falls in love a little faster than I do.

Tokens: [Text=If CharacterOffsetBegin=412 CharacterOffsetEnd=414 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=415 CharacterOffsetEnd=416 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=bring CharacterOffsetBegin=417 CharacterOffsetEnd=422 PartOfSpeech=VBP Lemma=bring NamedEntityTag=O SentimentClass=Positive] [Text=you CharacterOffsetBegin=423 CharacterOffsetEnd=426 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=home CharacterOffsetBegin=427 CharacterOffsetEnd=431 PartOfSpeech=NN Lemma=home NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=432 CharacterOffsetEnd=434 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=Mama CharacterOffsetBegin=435 CharacterOffsetEnd=439 PartOfSpeech=NN Lemma=mama NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=439 CharacterOffsetEnd=440 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=441 CharacterOffsetEnd=442 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=guess CharacterOffsetBegin=443 CharacterOffsetEnd=448 PartOfSpeech=VBP Lemma=guess NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=449 CharacterOffsetEnd=450 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=better CharacterOffsetBegin=451 CharacterOffsetEnd=457 PartOfSpeech=RB Lemma=better NamedEntityTag=O SentimentClass=Very positive] [Text=warn CharacterOffsetBegin=458 CharacterOffsetEnd=462 PartOfSpeech=VBP Lemma=warn NamedEntityTag=O SentimentClass=Negative] [Text=ya CharacterOffsetBegin=463 CharacterOffsetEnd=465 PartOfSpeech=PRP Lemma=ya NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=465 CharacterOffsetEnd=466 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=She CharacterOffsetBegin=467 CharacterOffsetEnd=470 PartOfSpeech=PRP Lemma=she NamedEntityTag=O SentimentClass=Neutral] [Text=falls CharacterOffsetBegin=471 CharacterOffsetEnd=476 PartOfSpeech=VBZ Lemma=fall NamedEntityTag=O SentimentClass=Negative] [Text=in CharacterOffsetBegin=477 CharacterOffsetEnd=479 PartOfSpeech=IN Lemma=in NamedEntityTag=O SentimentClass=Neutral] [Text=love CharacterOffsetBegin=480 CharacterOffsetEnd=484 PartOfSpeech=NN Lemma=love NamedEntityTag=O SentimentClass=Very positive] [Text=a CharacterOffsetBegin=485 CharacterOffsetEnd=486 PartOfSpeech=DT Lemma=a NamedEntityTag=O SentimentClass=Neutral] [Text=little CharacterOffsetBegin=487 CharacterOffsetEnd=493 PartOfSpeech=JJ Lemma=little NamedEntityTag=O SentimentClass=Neutral] [Text=faster CharacterOffsetBegin=494 CharacterOffsetEnd=500 PartOfSpeech=JJR Lemma=faster NamedEntityTag=O SentimentClass=Neutral] [Text=than CharacterOffsetBegin=501 CharacterOffsetEnd=505 PartOfSpeech=IN Lemma=than NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=506 CharacterOffsetEnd=507 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=do CharacterOffsetBegin=508 CharacterOffsetEnd=510 PartOfSpeech=VBP Lemma=do NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=510 CharacterOffsetEnd=511 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (SBAR (IN If) (S (NP (PRP I)) (VP (VBP bring) (NP (PRP you)) (ADVP (NN home) (TO to) (NN Mama))))) (, ,) (NP (PRP I)) (VP (VBP guess) (SBAR (S (NP (PRP I)) (ADVP (RB better)) (VP (VBP warn) (NP (PRP ya))))))) (, ,) (NP (PRP She)) (VP (VBZ falls) (PP (IN in) (NP (NP (NN love)) (ADJP (NP (DT a) (JJ little)) (JJR faster)))) (SBAR (IN than) (S (NP (PRP I)) (VP (VBP do))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.514    
(S sentiment=1 prob=0.721 (SBAR sentiment=2 prob=0.596
(IN sentiment=2 prob=0.997 If) (S sentiment=3 prob=0.540
(NP sentiment=2 prob=0.996 I) (VP sentiment=3 prob=0.531
(@VP sentiment=2 prob=0.770 (VBP sentiment=3 prob=0.927 bring)
(NP sentiment=2 prob=0.995 you)) (ADVP sentiment=2 prob=0.979
(NN sentiment=2 prob=0.995 home) (@ADVP sentiment=2 prob=0.987
(TO sentiment=2 prob=0.990 to) (NN sentiment=2 prob=0.990 Mama))))))
(@S sentiment=1 prob=0.619 (, sentiment=2 prob=0.997 ,)
(@S sentiment=1 prob=0.631 (NP sentiment=2 prob=0.996 I)
(VP sentiment=1 prob=0.542 (VBP sentiment=2 prob=0.980 guess)
(SBAR sentiment=2 prob=0.547 (NP sentiment=2 prob=0.996 I)
(@S sentiment=2 prob=0.662 (ADVP sentiment=4 prob=0.768 better)
(VP sentiment=2 prob=0.696 (VBP sentiment=1 prob=0.567 warn)
(NP sentiment=2 prob=0.945 ya)))))))) (@S sentiment=1 prob=0.542
(, sentiment=2 prob=0.997 ,) (@S sentiment=1 prob=0.459
(NP sentiment=2 prob=0.991 She) (@S sentiment=1 prob=0.755
(VP sentiment=1 prob=0.846 (@VP sentiment=1 prob=0.764
(VBZ sentiment=1 prob=0.925 falls) (PP sentiment=2 prob=0.678
(IN sentiment=2 prob=0.993 in) (NP sentiment=2 prob=0.601
(NP sentiment=4 prob=0.895 love) (ADJP sentiment=2 prob=0.888
(NP sentiment=2 prob=0.978 (DT sentiment=2 prob=0.990 a)
(JJ sentiment=2 prob=0.985 little)) (JJR sentiment=2 prob=0.990
faster))))) (SBAR sentiment=2 prob=0.956 (IN sentiment=2 prob=0.998
than) (S sentiment=2 prob=0.960 (NP sentiment=2 prob=0.996 I)
(VP sentiment=2 prob=0.992 do)))) (. sentiment=2 prob=0.997 .)))))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, falls-17) mark(bring-3, If-1) nsubj(bring-3, I-2) advcl:if(guess-10, bring-3) dobj(bring-3, you-4) dep(Mama-7, home-5) dep(Mama-7, to-6) advmod(bring-3, Mama-7) punct(guess-10, ,-8) nsubj(guess-10, I-9) ccomp(falls-17, guess-10) nsubj(warn-13, I-11) advmod(warn-13, better-12) ccomp(guess-10, warn-13) dobj(warn-13, ya-14) punct(falls-17, ,-15) nsubj(falls-17, She-16) case(love-19, in-18) nmod:in(falls-17, love-19) det(little-21, a-20) nmod:npmod(faster-22, little-21) amod(love-19, faster-22) mark(do-25, than-23) nsubj(do-25, I-24) advcl:than(falls-17, do-25) punct(falls-17, .-26)

Extracted the following NER entity mentions: She PERSON

Sentence #9 (27 tokens, sentiment: Negative): And my dad will check your tires, Pour you whiskey over ice, And take you fishing but pretend that he don’t like you.

Tokens: [Text=And CharacterOffsetBegin=512 CharacterOffsetEnd=515 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=my CharacterOffsetBegin=516 CharacterOffsetEnd=518 PartOfSpeech=PRP$ Lemma=my NamedEntityTag=O SentimentClass=Neutral] [Text=dad CharacterOffsetBegin=519 CharacterOffsetEnd=522 PartOfSpeech=NN Lemma=dad NamedEntityTag=O SentimentClass=Neutral] [Text=will CharacterOffsetBegin=523 CharacterOffsetEnd=527 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=check CharacterOffsetBegin=528 CharacterOffsetEnd=533 PartOfSpeech=VB Lemma=check NamedEntityTag=O SentimentClass=Positive] [Text=your CharacterOffsetBegin=534 CharacterOffsetEnd=538 PartOfSpeech=PRP$ Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=tires CharacterOffsetBegin=539 CharacterOffsetEnd=544 PartOfSpeech=NNS Lemma=tire NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=544 CharacterOffsetEnd=545 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=Pour CharacterOffsetBegin=546 CharacterOffsetEnd=550 PartOfSpeech=NNP Lemma=Pour NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=551 CharacterOffsetEnd=554 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=whiskey CharacterOffsetBegin=555 CharacterOffsetEnd=562 PartOfSpeech=NN Lemma=whiskey NamedEntityTag=O SentimentClass=Neutral] [Text=over CharacterOffsetBegin=563 CharacterOffsetEnd=567 PartOfSpeech=IN Lemma=over NamedEntityTag=O SentimentClass=Neutral] [Text=ice CharacterOffsetBegin=568 CharacterOffsetEnd=571 PartOfSpeech=NN Lemma=ice NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=571 CharacterOffsetEnd=572 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=And CharacterOffsetBegin=573 CharacterOffsetEnd=576 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=take CharacterOffsetBegin=577 CharacterOffsetEnd=581 PartOfSpeech=VB Lemma=take NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=582 CharacterOffsetEnd=585 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=fishing CharacterOffsetBegin=586 CharacterOffsetEnd=593 PartOfSpeech=NN Lemma=fishing NamedEntityTag=O SentimentClass=Neutral] [Text=but CharacterOffsetBegin=594 CharacterOffsetEnd=597 PartOfSpeech=CC Lemma=but NamedEntityTag=O SentimentClass=Neutral] [Text=pretend CharacterOffsetBegin=598 CharacterOffsetEnd=605 PartOfSpeech=VBP Lemma=pretend NamedEntityTag=O SentimentClass=Neutral] [Text=that CharacterOffsetBegin=606 CharacterOffsetEnd=610 PartOfSpeech=IN Lemma=that NamedEntityTag=O SentimentClass=Neutral] [Text=he CharacterOffsetBegin=611 CharacterOffsetEnd=613 PartOfSpeech=PRP Lemma=he NamedEntityTag=O SentimentClass=Neutral] [Text=do CharacterOffsetBegin=614 CharacterOffsetEnd=616 PartOfSpeech=VBP Lemma=do NamedEntityTag=O SentimentClass=Neutral] [Text=n’t CharacterOffsetBegin=616 CharacterOffsetEnd=619 PartOfSpeech=RB Lemma=not NamedEntityTag=O SentimentClass=Neutral] [Text=like CharacterOffsetBegin=620 CharacterOffsetEnd=624 PartOfSpeech=VB Lemma=like NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=625 CharacterOffsetEnd=628 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=628 CharacterOffsetEnd=629 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (CC And) (S (S (NP (PRP$ my) (NN dad)) (VP (MD will) (VP (VB check) (NP (PRP$ your) (NNS tires))))) (, ,) (S (NP (NNP Pour) (PRP you)) (NP (NP (NN whiskey)) (PP (IN over) (NP (NN ice)))))) (, ,) (CC And) (SINV (VP (VB take) (NP (PRP you))) (NP (NP (NN fishing)) (SBAR (CC but) (S (VP (VBP pretend) (SBAR (IN that) (S (NP (PRP he)) (VP (VBP do) (RB n’t) (VP (VB like) (NP (PRP you))))))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.535                            
(CC sentiment=2 prob=0.999 And) (@S sentiment=1 prob=0.454                        
(@S sentiment=1 prob=0.442 (@S sentiment=1 prob=0.650                        
(@S sentiment=1 prob=0.493 (S sentiment=1 prob=0.472                        
(@S sentiment=1 prob=0.408 (S sentiment=2 prob=0.393                        
(NP sentiment=2 prob=0.920                            
(PRP( sentiment=2 prob=0.998 my) (NN sentiment=2 prob=0.963 dad)) (VP sentiment=3 prob=0.425 (MD sentiment=2 prob=0.995 will) (VP sentiment=2 prob=0.427 (VB sentiment=3 prob=0.749 check) (NP sentiment=2 prob=0.917 (PRP) sentiment=2 prob=0.998
your) (NNS sentiment=2 prob=0.631 tires))))) (, sentiment=2 prob=0.997                        
,)) (S sentiment=2 prob=0.348 (NP sentiment=2 prob=0.632                        
(NNP sentiment=2 prob=0.631 Pour) (PRP sentiment=2 prob=0.995 you))                        
(NP sentiment=2 prob=0.557 (NP sentiment=2 prob=0.631 whiskey)                        
(PP sentiment=2 prob=0.986 (IN sentiment=2 prob=0.991 over)                        
(NP sentiment=2 prob=0.982 ice))))) (, sentiment=2 prob=0.997 ,))                        
(CC sentiment=2 prob=0.999 And)) (SINV sentiment=1 prob=0.480                        
(VP sentiment=2 prob=0.927 (VB sentiment=2 prob=0.994 take)                        
(NP sentiment=2 prob=0.995 you)) (NP sentiment=1 prob=0.495                        
(NP sentiment=2 prob=0.671 fishing) (SBAR sentiment=1 prob=0.522                        
(CC sentiment=2 prob=0.990 but) (S sentiment=1 prob=0.484                        
(VBP sentiment=2 prob=0.766 pretend) (SBAR sentiment=2 prob=0.550                        
(IN sentiment=2 prob=0.991 that) (S sentiment=2 prob=0.532                        
(NP sentiment=2 prob=0.993 he) (VP sentiment=1 prob=0.441                        
(@VP sentiment=2 prob=0.963 (VBP sentiment=2 prob=0.992 do)                        
(RB sentiment=2 prob=0.994 n’t)) (VP sentiment=2 prob=0.841                        
(VB sentiment=2 prob=0.995 like) (NP sentiment=2 prob=0.995                        
you)))))))))) (. sentiment=2 prob=0.997 .)))                            

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, check-5) cc(check-5, And-1) nmod:poss(dad-3, my-2) nsubj(check-5, dad-3) aux(check-5, will-4) nmod:poss(tires-7, your-6) dobj(check-5, tires-7) punct(check-5, ,-8) dep(whiskey-11, Pour-9) dep(Pour-9, you-10) parataxis(check-5, whiskey-11) case(ice-13, over-12) nmod:over(whiskey-11, ice-13) punct(check-5, ,-14) cc(check-5, And-15) conj:and(check-5, take-16) dobj(take-16, you-17) nsubj(take-16, fishing-18) cc(pretend-20, but-19) dep(fishing-18, pretend-20) mark(like-25, that-21) nsubj(like-25, he-22) aux(like-25, do-23) neg(like-25, n’t-24) ccomp(pretend-20, like-25) dobj(like-25, you-26) punct(check-5, .-27)

Extracted the following NER entity mentions: he PERSON

Sentence #10 (20 tokens, sentiment: Positive): If we break up, I’ll be fine; But you’ll be breaking more hearts than mine.

Tokens: [Text=If CharacterOffsetBegin=630 CharacterOffsetEnd=632 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=we CharacterOffsetBegin=633 CharacterOffsetEnd=635 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=break CharacterOffsetBegin=636 CharacterOffsetEnd=641 PartOfSpeech=VBP Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=up CharacterOffsetBegin=642 CharacterOffsetEnd=644 PartOfSpeech=RP Lemma=up NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=644 CharacterOffsetEnd=645 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=646 CharacterOffsetEnd=647 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=647 CharacterOffsetEnd=650 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=651 CharacterOffsetEnd=653 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=fine CharacterOffsetBegin=654 CharacterOffsetEnd=658 PartOfSpeech=JJ Lemma=fine NamedEntityTag=O SentimentClass=Positive] [Text=; CharacterOffsetBegin=658 CharacterOffsetEnd=659 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=But CharacterOffsetBegin=660 CharacterOffsetEnd=663 PartOfSpeech=CC Lemma=but NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=664 CharacterOffsetEnd=667 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=667 CharacterOffsetEnd=670 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=671 CharacterOffsetEnd=673 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=breaking CharacterOffsetBegin=674 CharacterOffsetEnd=682 PartOfSpeech=VBG Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=more CharacterOffsetBegin=683 CharacterOffsetEnd=687 PartOfSpeech=JJR Lemma=more NamedEntityTag=O SentimentClass=Neutral] [Text=hearts CharacterOffsetBegin=688 CharacterOffsetEnd=694 PartOfSpeech=NNS Lemma=heart NamedEntityTag=O SentimentClass=Positive] [Text=than CharacterOffsetBegin=695 CharacterOffsetEnd=699 PartOfSpeech=IN Lemma=than NamedEntityTag=O SentimentClass=Neutral] [Text=mine CharacterOffsetBegin=700 CharacterOffsetEnd=704 PartOfSpeech=NN Lemma=mine NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=704 CharacterOffsetEnd=705 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (SBAR (IN If) (S (NP (PRP we)) (VP (VBP break) (PRT (RP up))))) (, ,) (NP (PRP I)) (VP (MD ’ll) (VP (VB be) (ADJP (JJ fine))))) (: ;) (CC But) (S (NP (PRP you)) (VP (MD ’ll) (VP (VB be) (VP (VBG breaking) (NP (JJR more) (NNS hearts)) (PP (IN than) (NP (NN mine))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=3 prob=0.774    
(@S sentiment=3 prob=0.711 (@S sentiment=3 prob=0.746
(@S sentiment=3 prob=0.683 (S sentiment=3 prob=0.720
(SBAR sentiment=2 prob=0.908 (IN sentiment=2 prob=0.997 If)
(S sentiment=2 prob=0.853 (NP sentiment=2 prob=0.996 we)
(VP sentiment=2 prob=0.853 (VBP sentiment=2 prob=0.984 break)
(PRT sentiment=2 prob=0.997 up)))) (@S sentiment=3 prob=0.610
(, sentiment=2 prob=0.997 ,) (@S sentiment=3 prob=0.716
(NP sentiment=2 prob=0.996 I) (VP sentiment=3 prob=0.615
(MD sentiment=2 prob=0.998 ’ll) (VP sentiment=2 prob=0.609
(VB sentiment=2 prob=0.994 be) (ADJP sentiment=3 prob=0.894 fine))))))
(: sentiment=2 prob=0.997 ;)) (CC sentiment=2 prob=0.999 But))
(S sentiment=3 prob=0.412 (NP sentiment=2 prob=0.995 you)
(VP sentiment=2 prob=0.552 (MD sentiment=2 prob=0.998 ’ll)
(VP sentiment=2 prob=0.583 (VB sentiment=2 prob=0.994 be)
(VP sentiment=2 prob=0.463 (@VP sentiment=3 prob=0.456
(VBG sentiment=2 prob=0.962 breaking) (NP sentiment=2 prob=0.866
(JJR sentiment=2 prob=0.992 more) (NNS sentiment=3 prob=0.921 hearts)))
(PP sentiment=2 prob=0.982 (IN sentiment=2 prob=0.998 than)
(NP sentiment=2 prob=0.941 mine))))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, fine-9) mark(break-3, If-1) nsubj(break-3, we-2) advcl:if(fine-9, break-3) compound:prt(break-3, up-4) punct(fine-9, ,-5) nsubj(fine-9, I-6) aux(fine-9, ’ll-7) cop(fine-9, be-8) punct(fine-9, ;-10) cc(fine-9, But-11) nsubj(breaking-15, you-12) aux(breaking-15, ’ll-13) aux(breaking-15, be-14) conj:but(fine-9, breaking-15) amod(hearts-17, more-16) dobj(breaking-15, hearts-17) case(mine-19, than-18) nmod:than(breaking-15, mine-19) punct(fine-9, .-20)

Extracted the following NER entity mentions:

Sentence #11 (10 tokens, sentiment: Neutral): My sister’s gonna ask a million questions.

Tokens: [Text=My CharacterOffsetBegin=707 CharacterOffsetEnd=709 PartOfSpeech=PRP$ Lemma=my NamedEntityTag=O SentimentClass=Neutral] [Text=sister CharacterOffsetBegin=710 CharacterOffsetEnd=716 PartOfSpeech=NN Lemma=sister NamedEntityTag=O SentimentClass=Neutral] [Text=’s CharacterOffsetBegin=716 CharacterOffsetEnd=718 PartOfSpeech=POS Lemma=’s NamedEntityTag=O SentimentClass=Neutral] [Text=gon CharacterOffsetBegin=719 CharacterOffsetEnd=722 PartOfSpeech=VBG Lemma=gon NamedEntityTag=O SentimentClass=Neutral] [Text=na CharacterOffsetBegin=722 CharacterOffsetEnd=724 PartOfSpeech=TO Lemma=na NamedEntityTag=O SentimentClass=Neutral] [Text=ask CharacterOffsetBegin=725 CharacterOffsetEnd=728 PartOfSpeech=VB Lemma=ask NamedEntityTag=O SentimentClass=Neutral] [Text=a CharacterOffsetBegin=729 CharacterOffsetEnd=730 PartOfSpeech=DT Lemma=a NamedEntityTag=O SentimentClass=Neutral] [Text=million CharacterOffsetBegin=731 CharacterOffsetEnd=738 PartOfSpeech=CD Lemma=million NamedEntityTag=NUMBER NormalizedNamedEntityTag=1000000.0 SentimentClass=Neutral] [Text=questions CharacterOffsetBegin=739 CharacterOffsetEnd=748 PartOfSpeech=NNS Lemma=question NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=748 CharacterOffsetEnd=749 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (NP (NP (NP (PRP$ My)) (NP (NN sister) (POS ’s))) (VP (VBG gon) (S (VP (TO na) (VP (VB ask) (NP (QP (DT a) (CD million)) (NNS questions)))))) (. .)))

Sentiment-annotated binary tree: (ROOT|sentiment=2|prob=0.703 (@NP|sentiment=2|prob=0.772 (NP|sentiment=2|prob=0.992 (NP|sentiment=2|prob=0.997 My) (NP|sentiment=2|prob=0.978 (NN|sentiment=2|prob=0.989 sister) (POS|sentiment=2|prob=0.994 ’s))) (VP|sentiment=2|prob=0.633 (VBG|sentiment=2|prob=0.631 gon) (S|sentiment=2|prob=0.707 (TO|sentiment=2|prob=0.784 na) (VP|sentiment=2|prob=0.908 (VB|sentiment=2|prob=0.974 ask) (NP|sentiment=2|prob=0.923 (QP|sentiment=2|prob=0.982 (DT|sentiment=2|prob=0.990 a) (CD|sentiment=2|prob=0.973 million)) (NNS|sentiment=2|prob=0.993 questions)))))) (.|sentiment=2|prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, My-1) nmod:poss(My-1, sister-2) case(sister-2, ’s-3) acl(My-1, gon-4) mark(ask-6, na-5) xcomp(gon-4, ask-6) advmod(million-8, a-7) nummod(questions-9, million-8) dobj(ask-6, questions-9) punct(My-1, .-10)

Extracted the following NER entity mentions: million NUMBER

Sentence #12 (9 tokens, sentiment: Positive): Say anything she can to turn you red.

Tokens: [Text=Say CharacterOffsetBegin=750 CharacterOffsetEnd=753 PartOfSpeech=VB Lemma=say NamedEntityTag=O SentimentClass=Neutral] [Text=anything CharacterOffsetBegin=754 CharacterOffsetEnd=762 PartOfSpeech=NN Lemma=anything NamedEntityTag=O SentimentClass=Neutral] [Text=she CharacterOffsetBegin=763 CharacterOffsetEnd=766 PartOfSpeech=PRP Lemma=she NamedEntityTag=O SentimentClass=Neutral] [Text=can CharacterOffsetBegin=767 CharacterOffsetEnd=770 PartOfSpeech=MD Lemma=can NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=771 CharacterOffsetEnd=773 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=turn CharacterOffsetBegin=774 CharacterOffsetEnd=778 PartOfSpeech=VB Lemma=turn NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=779 CharacterOffsetEnd=782 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=red CharacterOffsetBegin=783 CharacterOffsetEnd=786 PartOfSpeech=JJ Lemma=red NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=786 CharacterOffsetEnd=787 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (VP (VB Say) (NP (NN anything)) (SBAR (S (NP (PRP she)) (VP (MD can) (S (VP (TO to) (VP (VB turn) (S (NP (PRP you)) (ADJP (JJ red)))))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=3 prob=0.364    
(VP sentiment=2 prob=0.424 (@VP sentiment=2 prob=0.783
(VB sentiment=2 prob=0.764 Say) (NP sentiment=2 prob=0.997 anything))
(SBAR sentiment=2 prob=0.700 (NP sentiment=2 prob=0.997 she)
(VP sentiment=2 prob=0.835 (MD sentiment=2 prob=0.997 can)
(S sentiment=2 prob=0.916 (TO sentiment=2 prob=0.990 to)
(VP sentiment=2 prob=0.929 (VB sentiment=2 prob=0.994 turn)
(S sentiment=2 prob=0.926 (NP sentiment=2 prob=0.995 you)
(ADJP sentiment=2 prob=0.986 red))))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, Say-1) dobj(Say-1, anything-2) nsubj(can-4, she-3) nsubj:xsubj(turn-6, she-3) dep(Say-1, can-4) mark(turn-6, to-5) xcomp(can-4, turn-6) nsubj(red-8, you-7) xcomp(turn-6, red-8) punct(Say-1, .-9)

Extracted the following NER entity mentions: she PERSON

Sentence #13 (29 tokens, sentiment: Negative): And when you meet my high school friends; They’ll buy you drinks and fill you in; On all the crazy nights I can’t outlive.

Tokens: [Text=And CharacterOffsetBegin=788 CharacterOffsetEnd=791 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=when CharacterOffsetBegin=792 CharacterOffsetEnd=796 PartOfSpeech=WRB Lemma=when NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=797 CharacterOffsetEnd=800 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=meet CharacterOffsetBegin=801 CharacterOffsetEnd=805 PartOfSpeech=VBP Lemma=meet NamedEntityTag=O SentimentClass=Neutral] [Text=my CharacterOffsetBegin=806 CharacterOffsetEnd=808 PartOfSpeech=PRP$ Lemma=my NamedEntityTag=O SentimentClass=Neutral] [Text=high CharacterOffsetBegin=809 CharacterOffsetEnd=813 PartOfSpeech=JJ Lemma=high NamedEntityTag=O SentimentClass=Positive] [Text=school CharacterOffsetBegin=814 CharacterOffsetEnd=820 PartOfSpeech=NN Lemma=school NamedEntityTag=O SentimentClass=Neutral] [Text=friends CharacterOffsetBegin=821 CharacterOffsetEnd=828 PartOfSpeech=NNS Lemma=friend NamedEntityTag=O SentimentClass=Positive] [Text=; CharacterOffsetBegin=828 CharacterOffsetEnd=829 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=They CharacterOffsetBegin=830 CharacterOffsetEnd=834 PartOfSpeech=PRP Lemma=they NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=834 CharacterOffsetEnd=837 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=buy CharacterOffsetBegin=838 CharacterOffsetEnd=841 PartOfSpeech=VB Lemma=buy NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=842 CharacterOffsetEnd=845 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=drinks CharacterOffsetBegin=846 CharacterOffsetEnd=852 PartOfSpeech=NNS Lemma=drink NamedEntityTag=O SentimentClass=Neutral] [Text=and CharacterOffsetBegin=853 CharacterOffsetEnd=856 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=fill CharacterOffsetBegin=857 CharacterOffsetEnd=861 PartOfSpeech=VB Lemma=fill NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=862 CharacterOffsetEnd=865 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=in CharacterOffsetBegin=866 CharacterOffsetEnd=868 PartOfSpeech=IN Lemma=in NamedEntityTag=O SentimentClass=Neutral] [Text=; CharacterOffsetBegin=868 CharacterOffsetEnd=869 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=On CharacterOffsetBegin=870 CharacterOffsetEnd=872 PartOfSpeech=IN Lemma=on NamedEntityTag=O SentimentClass=Neutral] [Text=all CharacterOffsetBegin=873 CharacterOffsetEnd=876 PartOfSpeech=PDT Lemma=all NamedEntityTag=O SentimentClass=Neutral] [Text=the CharacterOffsetBegin=877 CharacterOffsetEnd=880 PartOfSpeech=DT Lemma=the NamedEntityTag=O SentimentClass=Neutral] [Text=crazy CharacterOffsetBegin=881 CharacterOffsetEnd=886 PartOfSpeech=JJ Lemma=crazy NamedEntityTag=O SentimentClass=Neutral] [Text=nights CharacterOffsetBegin=887 CharacterOffsetEnd=893 PartOfSpeech=NNS Lemma=night NamedEntityTag=TIME NormalizedNamedEntityTag=TNI Timex=nights SentimentClass=Neutral] [Text=I CharacterOffsetBegin=894 CharacterOffsetEnd=895 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=ca CharacterOffsetBegin=896 CharacterOffsetEnd=898 PartOfSpeech=MD Lemma=can NamedEntityTag=O SentimentClass=Neutral] [Text=n’t CharacterOffsetBegin=898 CharacterOffsetEnd=901 PartOfSpeech=RB Lemma=not NamedEntityTag=O SentimentClass=Neutral] [Text=outlive CharacterOffsetBegin=902 CharacterOffsetEnd=909 PartOfSpeech=VB Lemma=outlive NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=909 CharacterOffsetEnd=910 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (CC And) (SBAR (WHADVP (WRB when)) (S (NP (PRP you)) (VP (VBP meet) (NP (PRP$ my) (JJ high) (NN school) (NNS friends))))) (: ;) (NP (PRP They)) (VP (MD ’ll) (VP (VP (VB buy) (S (NP (PRP you)) (NP (NNS drinks)))) (CC and) (VP (VB fill) (NP (PRP you)) (SBAR (IN in) (S (: ;) (PP (IN On) (NP (PDT all) (DT the) (JJ crazy) (NNS nights))) (NP (PRP I)) (VP (MD ca) (RB n’t) (VP (VB outlive)))))))) (. .)))

Sentiment-annotated binary tree: (ROOT|sentiment=1|prob=0.713 (CC|sentiment=2|prob=0.999 And) (@S|sentiment=1|prob=0.635 (SBAR|sentiment=2|prob=0.928 (WHADVP|sentiment=2|prob=0.993 when) (S|sentiment=2|prob=0.857 (NP|sentiment=2|prob=0.995 you) (VP|sentiment=2|prob=0.945 (VBP|sentiment=2|prob=0.957 meet) (NP|sentiment=2|prob=0.822 (PRP$|sentiment=2|prob=0.998 my) (@NP|sentiment=2|prob=0.709 (JJ|sentiment=3|prob=0.955 high) (@NP|sentiment=2|prob=0.798 (NN|sentiment=2|prob=0.979 school) (NNS|sentiment=3|prob=0.756 friends))))))) (@S|sentiment=1|prob=0.546 (:|sentiment=2|prob=0.997 ;) (@S|sentiment=1|prob=0.638 (NP|sentiment=2|prob=0.993 They) (@S|sentiment=1|prob=0.488 (VP|sentiment=1|prob=0.495 (MD|sentiment=2|prob=0.998 ’ll) (VP|sentiment=1|prob=0.529 (@VP|sentiment=2|prob=0.687 (VP|sentiment=2|prob=0.659 (VB|sentiment=2|prob=0.972 buy) (S|sentiment=2|prob=0.740 (NP|sentiment=2|prob=0.995 you) (NP|sentiment=2|prob=0.631 drinks))) (CC|sentiment=2|prob=0.996 and)) (VP|sentiment=2|prob=0.453 (@VP|sentiment=2|prob=0.927 (VB|sentiment=2|prob=0.974 fill) (NP|sentiment=2|prob=0.995 you)) (SBAR|sentiment=2|prob=0.474 (IN|sentiment=2|prob=0.993 in) (S|sentiment=2|prob=0.476 (:|sentiment=2|prob=0.997 ;) (@S|sentiment=1|prob=0.387 (PP|sentiment=2|prob=0.947 (IN|sentiment=2|prob=0.997 On) (NP|sentiment=2|prob=0.937 (PDT|sentiment=2|prob=0.995 all) (@NP|sentiment=2|prob=0.966 (DT|sentiment=2|prob=0.994 the) (@NP|sentiment=2|prob=0.880 (JJ|sentiment=2|prob=0.987 crazy) (NNS|sentiment=2|prob=0.963 nights))))) (@S|sentiment=2|prob=0.533 (NP|sentiment=2|prob=0.996 I) (VP|sentiment=2|prob=0.648 (@VP|sentiment=2|prob=0.987 (MD|sentiment=2|prob=0.998 ca) (RB|sentiment=2|prob=0.994 n’t)) (VP|sentiment=2|prob=0.631 outlive))))))))) (.|sentiment=2|prob=0.997 .))))))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, buy-12) cc(buy-12, And-1) advmod(meet-4, when-2) nsubj(meet-4, you-3) advcl(buy-12, meet-4) nmod:poss(friends-8, my-5) amod(friends-8, high-6) compound(friends-8, school-7) dobj(meet-4, friends-8) punct(buy-12, ;-9) nsubj(buy-12, They-10) nsubj(fill-16, They-10) aux(buy-12, ’ll-11) nsubj(drinks-14, you-13) xcomp(buy-12, drinks-14) cc(buy-12, and-15) conj:and(buy-12, fill-16) dobj(fill-16, you-17) mark(outlive-28, in-18) punct(outlive-28, ;-19) case(nights-24, On-20) det:predet(nights-24, all-21) det(nights-24, the-22) amod(nights-24, crazy-23) nmod:on(outlive-28, nights-24) nsubj(outlive-28, I-25) aux(outlive-28, ca-26) neg(outlive-28, n’t-27) advcl:in(fill-16, outlive-28) punct(buy-12, .-29)

Extracted the following NER entity mentions: nights TIME

Sentence #14 (26 tokens, sentiment: Negative): If I bring you home to Mama, I guess I better warn ya, She falls in love a little faster than I do.

Tokens: [Text=If CharacterOffsetBegin=912 CharacterOffsetEnd=914 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=915 CharacterOffsetEnd=916 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=bring CharacterOffsetBegin=917 CharacterOffsetEnd=922 PartOfSpeech=VBP Lemma=bring NamedEntityTag=O SentimentClass=Positive] [Text=you CharacterOffsetBegin=923 CharacterOffsetEnd=926 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=home CharacterOffsetBegin=927 CharacterOffsetEnd=931 PartOfSpeech=NN Lemma=home NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=932 CharacterOffsetEnd=934 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=Mama CharacterOffsetBegin=935 CharacterOffsetEnd=939 PartOfSpeech=NN Lemma=mama NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=939 CharacterOffsetEnd=940 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=941 CharacterOffsetEnd=942 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=guess CharacterOffsetBegin=943 CharacterOffsetEnd=948 PartOfSpeech=VBP Lemma=guess NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=949 CharacterOffsetEnd=950 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=better CharacterOffsetBegin=951 CharacterOffsetEnd=957 PartOfSpeech=RB Lemma=better NamedEntityTag=O SentimentClass=Very positive] [Text=warn CharacterOffsetBegin=958 CharacterOffsetEnd=962 PartOfSpeech=VBP Lemma=warn NamedEntityTag=O SentimentClass=Negative] [Text=ya CharacterOffsetBegin=963 CharacterOffsetEnd=965 PartOfSpeech=PRP Lemma=ya NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=965 CharacterOffsetEnd=966 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=She CharacterOffsetBegin=967 CharacterOffsetEnd=970 PartOfSpeech=PRP Lemma=she NamedEntityTag=O SentimentClass=Neutral] [Text=falls CharacterOffsetBegin=971 CharacterOffsetEnd=976 PartOfSpeech=VBZ Lemma=fall NamedEntityTag=O SentimentClass=Negative] [Text=in CharacterOffsetBegin=977 CharacterOffsetEnd=979 PartOfSpeech=IN Lemma=in NamedEntityTag=O SentimentClass=Neutral] [Text=love CharacterOffsetBegin=980 CharacterOffsetEnd=984 PartOfSpeech=NN Lemma=love NamedEntityTag=O SentimentClass=Very positive] [Text=a CharacterOffsetBegin=985 CharacterOffsetEnd=986 PartOfSpeech=DT Lemma=a NamedEntityTag=O SentimentClass=Neutral] [Text=little CharacterOffsetBegin=987 CharacterOffsetEnd=993 PartOfSpeech=JJ Lemma=little NamedEntityTag=O SentimentClass=Neutral] [Text=faster CharacterOffsetBegin=994 CharacterOffsetEnd=1000 PartOfSpeech=JJR Lemma=faster NamedEntityTag=O SentimentClass=Neutral] [Text=than CharacterOffsetBegin=1001 CharacterOffsetEnd=1005 PartOfSpeech=IN Lemma=than NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1006 CharacterOffsetEnd=1007 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=do CharacterOffsetBegin=1008 CharacterOffsetEnd=1010 PartOfSpeech=VBP Lemma=do NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1010 CharacterOffsetEnd=1011 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (SBAR (IN If) (S (NP (PRP I)) (VP (VBP bring) (NP (PRP you)) (ADVP (NN home) (TO to) (NN Mama))))) (, ,) (NP (PRP I)) (VP (VBP guess) (SBAR (S (NP (PRP I)) (ADVP (RB better)) (VP (VBP warn) (NP (PRP ya))))))) (, ,) (NP (PRP She)) (VP (VBZ falls) (PP (IN in) (NP (NP (NN love)) (ADJP (NP (DT a) (JJ little)) (JJR faster)))) (SBAR (IN than) (S (NP (PRP I)) (VP (VBP do))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.514    
(S sentiment=1 prob=0.721 (SBAR sentiment=2 prob=0.596
(IN sentiment=2 prob=0.997 If) (S sentiment=3 prob=0.540
(NP sentiment=2 prob=0.996 I) (VP sentiment=3 prob=0.531
(@VP sentiment=2 prob=0.770 (VBP sentiment=3 prob=0.927 bring)
(NP sentiment=2 prob=0.995 you)) (ADVP sentiment=2 prob=0.979
(NN sentiment=2 prob=0.995 home) (@ADVP sentiment=2 prob=0.987
(TO sentiment=2 prob=0.990 to) (NN sentiment=2 prob=0.990 Mama))))))
(@S sentiment=1 prob=0.619 (, sentiment=2 prob=0.997 ,)
(@S sentiment=1 prob=0.631 (NP sentiment=2 prob=0.996 I)
(VP sentiment=1 prob=0.542 (VBP sentiment=2 prob=0.980 guess)
(SBAR sentiment=2 prob=0.547 (NP sentiment=2 prob=0.996 I)
(@S sentiment=2 prob=0.662 (ADVP sentiment=4 prob=0.768 better)
(VP sentiment=2 prob=0.696 (VBP sentiment=1 prob=0.567 warn)
(NP sentiment=2 prob=0.945 ya)))))))) (@S sentiment=1 prob=0.542
(, sentiment=2 prob=0.997 ,) (@S sentiment=1 prob=0.459
(NP sentiment=2 prob=0.991 She) (@S sentiment=1 prob=0.755
(VP sentiment=1 prob=0.846 (@VP sentiment=1 prob=0.764
(VBZ sentiment=1 prob=0.925 falls) (PP sentiment=2 prob=0.678
(IN sentiment=2 prob=0.993 in) (NP sentiment=2 prob=0.601
(NP sentiment=4 prob=0.895 love) (ADJP sentiment=2 prob=0.888
(NP sentiment=2 prob=0.978 (DT sentiment=2 prob=0.990 a)
(JJ sentiment=2 prob=0.985 little)) (JJR sentiment=2 prob=0.990
faster))))) (SBAR sentiment=2 prob=0.956 (IN sentiment=2 prob=0.998
than) (S sentiment=2 prob=0.960 (NP sentiment=2 prob=0.996 I)
(VP sentiment=2 prob=0.992 do)))) (. sentiment=2 prob=0.997 .)))))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, falls-17) mark(bring-3, If-1) nsubj(bring-3, I-2) advcl:if(guess-10, bring-3) dobj(bring-3, you-4) dep(Mama-7, home-5) dep(Mama-7, to-6) advmod(bring-3, Mama-7) punct(guess-10, ,-8) nsubj(guess-10, I-9) ccomp(falls-17, guess-10) nsubj(warn-13, I-11) advmod(warn-13, better-12) ccomp(guess-10, warn-13) dobj(warn-13, ya-14) punct(falls-17, ,-15) nsubj(falls-17, She-16) case(love-19, in-18) nmod:in(falls-17, love-19) det(little-21, a-20) nmod:npmod(faster-22, little-21) amod(love-19, faster-22) mark(do-25, than-23) nsubj(do-25, I-24) advcl:than(falls-17, do-25) punct(falls-17, .-26)

Extracted the following NER entity mentions: She PERSON

Sentence #15 (27 tokens, sentiment: Negative): And my dad will check your tires, Pour you whiskey over ice, And take you fishing but pretend that he don’t like you.

Tokens: [Text=And CharacterOffsetBegin=1012 CharacterOffsetEnd=1015 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=my CharacterOffsetBegin=1016 CharacterOffsetEnd=1018 PartOfSpeech=PRP$ Lemma=my NamedEntityTag=O SentimentClass=Neutral] [Text=dad CharacterOffsetBegin=1019 CharacterOffsetEnd=1022 PartOfSpeech=NN Lemma=dad NamedEntityTag=O SentimentClass=Neutral] [Text=will CharacterOffsetBegin=1023 CharacterOffsetEnd=1027 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=check CharacterOffsetBegin=1028 CharacterOffsetEnd=1033 PartOfSpeech=VB Lemma=check NamedEntityTag=O SentimentClass=Positive] [Text=your CharacterOffsetBegin=1034 CharacterOffsetEnd=1038 PartOfSpeech=PRP$ Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=tires CharacterOffsetBegin=1039 CharacterOffsetEnd=1044 PartOfSpeech=NNS Lemma=tire NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1044 CharacterOffsetEnd=1045 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=Pour CharacterOffsetBegin=1046 CharacterOffsetEnd=1050 PartOfSpeech=NNP Lemma=Pour NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=1051 CharacterOffsetEnd=1054 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=whiskey CharacterOffsetBegin=1055 CharacterOffsetEnd=1062 PartOfSpeech=NN Lemma=whiskey NamedEntityTag=O SentimentClass=Neutral] [Text=over CharacterOffsetBegin=1063 CharacterOffsetEnd=1067 PartOfSpeech=IN Lemma=over NamedEntityTag=O SentimentClass=Neutral] [Text=ice CharacterOffsetBegin=1068 CharacterOffsetEnd=1071 PartOfSpeech=NN Lemma=ice NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1071 CharacterOffsetEnd=1072 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=And CharacterOffsetBegin=1073 CharacterOffsetEnd=1076 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=take CharacterOffsetBegin=1077 CharacterOffsetEnd=1081 PartOfSpeech=VB Lemma=take NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=1082 CharacterOffsetEnd=1085 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=fishing CharacterOffsetBegin=1086 CharacterOffsetEnd=1093 PartOfSpeech=NN Lemma=fishing NamedEntityTag=O SentimentClass=Neutral] [Text=but CharacterOffsetBegin=1094 CharacterOffsetEnd=1097 PartOfSpeech=CC Lemma=but NamedEntityTag=O SentimentClass=Neutral] [Text=pretend CharacterOffsetBegin=1098 CharacterOffsetEnd=1105 PartOfSpeech=VBP Lemma=pretend NamedEntityTag=O SentimentClass=Neutral] [Text=that CharacterOffsetBegin=1106 CharacterOffsetEnd=1110 PartOfSpeech=IN Lemma=that NamedEntityTag=O SentimentClass=Neutral] [Text=he CharacterOffsetBegin=1111 CharacterOffsetEnd=1113 PartOfSpeech=PRP Lemma=he NamedEntityTag=O SentimentClass=Neutral] [Text=do CharacterOffsetBegin=1114 CharacterOffsetEnd=1116 PartOfSpeech=VBP Lemma=do NamedEntityTag=O SentimentClass=Neutral] [Text=n’t CharacterOffsetBegin=1116 CharacterOffsetEnd=1119 PartOfSpeech=RB Lemma=not NamedEntityTag=O SentimentClass=Neutral] [Text=like CharacterOffsetBegin=1120 CharacterOffsetEnd=1124 PartOfSpeech=VB Lemma=like NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=1125 CharacterOffsetEnd=1128 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1128 CharacterOffsetEnd=1129 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (CC And) (S (S (NP (PRP$ my) (NN dad)) (VP (MD will) (VP (VB check) (NP (PRP$ your) (NNS tires))))) (, ,) (S (NP (NNP Pour) (PRP you)) (NP (NP (NN whiskey)) (PP (IN over) (NP (NN ice)))))) (, ,) (CC And) (SINV (VP (VB take) (NP (PRP you))) (NP (NP (NN fishing)) (SBAR (CC but) (S (VP (VBP pretend) (SBAR (IN that) (S (NP (PRP he)) (VP (VBP do) (RB n’t) (VP (VB like) (NP (PRP you))))))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.535                            
(CC sentiment=2 prob=0.999 And) (@S sentiment=1 prob=0.454                        
(@S sentiment=1 prob=0.442 (@S sentiment=1 prob=0.650                        
(@S sentiment=1 prob=0.493 (S sentiment=1 prob=0.472                        
(@S sentiment=1 prob=0.408 (S sentiment=2 prob=0.393                        
(NP sentiment=2 prob=0.920                            
(PRP( sentiment=2 prob=0.998 my) (NN sentiment=2 prob=0.963 dad)) (VP sentiment=3 prob=0.425 (MD sentiment=2 prob=0.995 will) (VP sentiment=2 prob=0.427 (VB sentiment=3 prob=0.749 check) (NP sentiment=2 prob=0.917 (PRP) sentiment=2 prob=0.998
your) (NNS sentiment=2 prob=0.631 tires))))) (, sentiment=2 prob=0.997                        
,)) (S sentiment=2 prob=0.348 (NP sentiment=2 prob=0.632                        
(NNP sentiment=2 prob=0.631 Pour) (PRP sentiment=2 prob=0.995 you))                        
(NP sentiment=2 prob=0.557 (NP sentiment=2 prob=0.631 whiskey)                        
(PP sentiment=2 prob=0.986 (IN sentiment=2 prob=0.991 over)                        
(NP sentiment=2 prob=0.982 ice))))) (, sentiment=2 prob=0.997 ,))                        
(CC sentiment=2 prob=0.999 And)) (SINV sentiment=1 prob=0.480                        
(VP sentiment=2 prob=0.927 (VB sentiment=2 prob=0.994 take)                        
(NP sentiment=2 prob=0.995 you)) (NP sentiment=1 prob=0.495                        
(NP sentiment=2 prob=0.671 fishing) (SBAR sentiment=1 prob=0.522                        
(CC sentiment=2 prob=0.990 but) (S sentiment=1 prob=0.484                        
(VBP sentiment=2 prob=0.766 pretend) (SBAR sentiment=2 prob=0.550                        
(IN sentiment=2 prob=0.991 that) (S sentiment=2 prob=0.532                        
(NP sentiment=2 prob=0.993 he) (VP sentiment=1 prob=0.441                        
(@VP sentiment=2 prob=0.963 (VBP sentiment=2 prob=0.992 do)                        
(RB sentiment=2 prob=0.994 n’t)) (VP sentiment=2 prob=0.841                        
(VB sentiment=2 prob=0.995 like) (NP sentiment=2 prob=0.995                        
you)))))))))) (. sentiment=2 prob=0.997 .)))                            

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, check-5) cc(check-5, And-1) nmod:poss(dad-3, my-2) nsubj(check-5, dad-3) aux(check-5, will-4) nmod:poss(tires-7, your-6) dobj(check-5, tires-7) punct(check-5, ,-8) dep(whiskey-11, Pour-9) dep(Pour-9, you-10) parataxis(check-5, whiskey-11) case(ice-13, over-12) nmod:over(whiskey-11, ice-13) punct(check-5, ,-14) cc(check-5, And-15) conj:and(check-5, take-16) dobj(take-16, you-17) nsubj(take-16, fishing-18) cc(pretend-20, but-19) dep(fishing-18, pretend-20) mark(like-25, that-21) nsubj(like-25, he-22) aux(like-25, do-23) neg(like-25, n’t-24) ccomp(pretend-20, like-25) dobj(like-25, you-26) punct(check-5, .-27)

Extracted the following NER entity mentions: he PERSON

Sentence #16 (20 tokens, sentiment: Positive): If we break up, I’ll be fine; But you’ll be breaking more hearts than mine.

Tokens: [Text=If CharacterOffsetBegin=1130 CharacterOffsetEnd=1132 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=we CharacterOffsetBegin=1133 CharacterOffsetEnd=1135 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=break CharacterOffsetBegin=1136 CharacterOffsetEnd=1141 PartOfSpeech=VBP Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=up CharacterOffsetBegin=1142 CharacterOffsetEnd=1144 PartOfSpeech=RP Lemma=up NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1144 CharacterOffsetEnd=1145 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1146 CharacterOffsetEnd=1147 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=1147 CharacterOffsetEnd=1150 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=1151 CharacterOffsetEnd=1153 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=fine CharacterOffsetBegin=1154 CharacterOffsetEnd=1158 PartOfSpeech=JJ Lemma=fine NamedEntityTag=O SentimentClass=Positive] [Text=; CharacterOffsetBegin=1158 CharacterOffsetEnd=1159 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=But CharacterOffsetBegin=1160 CharacterOffsetEnd=1163 PartOfSpeech=CC Lemma=but NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=1164 CharacterOffsetEnd=1167 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=1167 CharacterOffsetEnd=1170 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=1171 CharacterOffsetEnd=1173 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=breaking CharacterOffsetBegin=1174 CharacterOffsetEnd=1182 PartOfSpeech=VBG Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=more CharacterOffsetBegin=1183 CharacterOffsetEnd=1187 PartOfSpeech=JJR Lemma=more NamedEntityTag=O SentimentClass=Neutral] [Text=hearts CharacterOffsetBegin=1188 CharacterOffsetEnd=1194 PartOfSpeech=NNS Lemma=heart NamedEntityTag=O SentimentClass=Positive] [Text=than CharacterOffsetBegin=1195 CharacterOffsetEnd=1199 PartOfSpeech=IN Lemma=than NamedEntityTag=O SentimentClass=Neutral] [Text=mine CharacterOffsetBegin=1200 CharacterOffsetEnd=1204 PartOfSpeech=NN Lemma=mine NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1204 CharacterOffsetEnd=1205 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (SBAR (IN If) (S (NP (PRP we)) (VP (VBP break) (PRT (RP up))))) (, ,) (NP (PRP I)) (VP (MD ’ll) (VP (VB be) (ADJP (JJ fine))))) (: ;) (CC But) (S (NP (PRP you)) (VP (MD ’ll) (VP (VB be) (VP (VBG breaking) (NP (JJR more) (NNS hearts)) (PP (IN than) (NP (NN mine))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=3 prob=0.774    
(@S sentiment=3 prob=0.711 (@S sentiment=3 prob=0.746
(@S sentiment=3 prob=0.683 (S sentiment=3 prob=0.720
(SBAR sentiment=2 prob=0.908 (IN sentiment=2 prob=0.997 If)
(S sentiment=2 prob=0.853 (NP sentiment=2 prob=0.996 we)
(VP sentiment=2 prob=0.853 (VBP sentiment=2 prob=0.984 break)
(PRT sentiment=2 prob=0.997 up)))) (@S sentiment=3 prob=0.610
(, sentiment=2 prob=0.997 ,) (@S sentiment=3 prob=0.716
(NP sentiment=2 prob=0.996 I) (VP sentiment=3 prob=0.615
(MD sentiment=2 prob=0.998 ’ll) (VP sentiment=2 prob=0.609
(VB sentiment=2 prob=0.994 be) (ADJP sentiment=3 prob=0.894 fine))))))
(: sentiment=2 prob=0.997 ;)) (CC sentiment=2 prob=0.999 But))
(S sentiment=3 prob=0.412 (NP sentiment=2 prob=0.995 you)
(VP sentiment=2 prob=0.552 (MD sentiment=2 prob=0.998 ’ll)
(VP sentiment=2 prob=0.583 (VB sentiment=2 prob=0.994 be)
(VP sentiment=2 prob=0.463 (@VP sentiment=3 prob=0.456
(VBG sentiment=2 prob=0.962 breaking) (NP sentiment=2 prob=0.866
(JJR sentiment=2 prob=0.992 more) (NNS sentiment=3 prob=0.921 hearts)))
(PP sentiment=2 prob=0.982 (IN sentiment=2 prob=0.998 than)
(NP sentiment=2 prob=0.941 mine))))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, fine-9) mark(break-3, If-1) nsubj(break-3, we-2) advcl:if(fine-9, break-3) compound:prt(break-3, up-4) punct(fine-9, ,-5) nsubj(fine-9, I-6) aux(fine-9, ’ll-7) cop(fine-9, be-8) punct(fine-9, ;-10) cc(fine-9, But-11) nsubj(breaking-15, you-12) aux(breaking-15, ’ll-13) aux(breaking-15, be-14) conj:but(fine-9, breaking-15) amod(hearts-17, more-16) dobj(breaking-15, hearts-17) case(mine-19, than-18) nmod:than(breaking-15, mine-19) punct(fine-9, .-20)

Extracted the following NER entity mentions:

Sentence #17 (23 tokens, sentiment: Negative): If I bring you home to Mama, I guess I better warn ya; She feels every heartache I go through.

Tokens: [Text=If CharacterOffsetBegin=1207 CharacterOffsetEnd=1209 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1210 CharacterOffsetEnd=1211 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=bring CharacterOffsetBegin=1212 CharacterOffsetEnd=1217 PartOfSpeech=VBP Lemma=bring NamedEntityTag=O SentimentClass=Positive] [Text=you CharacterOffsetBegin=1218 CharacterOffsetEnd=1221 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=home CharacterOffsetBegin=1222 CharacterOffsetEnd=1226 PartOfSpeech=NN Lemma=home NamedEntityTag=O SentimentClass=Neutral] [Text=to CharacterOffsetBegin=1227 CharacterOffsetEnd=1229 PartOfSpeech=TO Lemma=to NamedEntityTag=O SentimentClass=Neutral] [Text=Mama CharacterOffsetBegin=1230 CharacterOffsetEnd=1234 PartOfSpeech=NN Lemma=mama NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1234 CharacterOffsetEnd=1235 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1236 CharacterOffsetEnd=1237 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=guess CharacterOffsetBegin=1238 CharacterOffsetEnd=1243 PartOfSpeech=VBP Lemma=guess NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1244 CharacterOffsetEnd=1245 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=better CharacterOffsetBegin=1246 CharacterOffsetEnd=1252 PartOfSpeech=RB Lemma=better NamedEntityTag=O SentimentClass=Very positive] [Text=warn CharacterOffsetBegin=1253 CharacterOffsetEnd=1257 PartOfSpeech=VBP Lemma=warn NamedEntityTag=O SentimentClass=Negative] [Text=ya CharacterOffsetBegin=1258 CharacterOffsetEnd=1260 PartOfSpeech=PRP Lemma=ya NamedEntityTag=O SentimentClass=Neutral] [Text=; CharacterOffsetBegin=1260 CharacterOffsetEnd=1261 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=She CharacterOffsetBegin=1262 CharacterOffsetEnd=1265 PartOfSpeech=PRP Lemma=she NamedEntityTag=O SentimentClass=Neutral] [Text=feels CharacterOffsetBegin=1266 CharacterOffsetEnd=1271 PartOfSpeech=VBZ Lemma=feel NamedEntityTag=O SentimentClass=Neutral] [Text=every CharacterOffsetBegin=1272 CharacterOffsetEnd=1277 PartOfSpeech=DT Lemma=every NamedEntityTag=O SentimentClass=Neutral] [Text=heartache CharacterOffsetBegin=1278 CharacterOffsetEnd=1287 PartOfSpeech=NN Lemma=heartache NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1288 CharacterOffsetEnd=1289 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=go CharacterOffsetBegin=1290 CharacterOffsetEnd=1292 PartOfSpeech=VBP Lemma=go NamedEntityTag=O SentimentClass=Neutral] [Text=through CharacterOffsetBegin=1293 CharacterOffsetEnd=1300 PartOfSpeech=IN Lemma=through NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1300 CharacterOffsetEnd=1301 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (SBAR (IN If) (S (NP (PRP I)) (VP (VBP bring) (NP (PRP you)) (ADVP (NN home) (TO to) (NN Mama))))) (, ,) (NP (PRP I)) (VP (VBP guess) (SBAR (S (NP (PRP I)) (ADVP (RB better)) (VP (VBP warn) (NP (PRP ya))))))) (: ;) (S (NP (PRP She)) (VP (VBZ feels) (NP (NP (DT every) (NN heartache)) (SBAR (S (NP (PRP I)) (VP (VBP go) (PP (IN through)))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.555    
(@S sentiment=1 prob=0.527 (@S sentiment=1 prob=0.566
(S sentiment=1 prob=0.721 (SBAR sentiment=2 prob=0.596
(IN sentiment=2 prob=0.997 If) (S sentiment=3 prob=0.540
(NP sentiment=2 prob=0.996 I) (VP sentiment=3 prob=0.531
(@VP sentiment=2 prob=0.770 (VBP sentiment=3 prob=0.927 bring)
(NP sentiment=2 prob=0.995 you)) (ADVP sentiment=2 prob=0.979
(NN sentiment=2 prob=0.995 home) (@ADVP sentiment=2 prob=0.987
(TO sentiment=2 prob=0.990 to) (NN sentiment=2 prob=0.990 Mama))))))
(@S sentiment=1 prob=0.619 (, sentiment=2 prob=0.997 ,)
(@S sentiment=1 prob=0.631 (NP sentiment=2 prob=0.996 I)
(VP sentiment=1 prob=0.542 (VBP sentiment=2 prob=0.980 guess)
(SBAR sentiment=2 prob=0.547 (NP sentiment=2 prob=0.996 I)
(@S sentiment=2 prob=0.662 (ADVP sentiment=4 prob=0.768 better)
(VP sentiment=2 prob=0.696 (VBP sentiment=1 prob=0.567 warn)
(NP sentiment=2 prob=0.945 ya)))))))) (: sentiment=2 prob=0.997 ;))
(S sentiment=2 prob=0.620 (NP sentiment=2 prob=0.991 She)
(VP sentiment=2 prob=0.541 (VBZ sentiment=2 prob=0.999 feels)
(NP sentiment=2 prob=0.816 (NP sentiment=2 prob=0.957
(DT sentiment=2 prob=0.998 every) (NN sentiment=2 prob=0.922 heartache))
(SBAR sentiment=2 prob=0.840 (NP sentiment=2 prob=0.996 I)
(VP sentiment=2 prob=0.951 (VBP sentiment=2 prob=0.997 go)
(PP sentiment=2 prob=0.997 through))))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, guess-10) mark(bring-3, If-1) nsubj(bring-3, I-2) advcl:if(guess-10, bring-3) dobj(bring-3, you-4) dep(Mama-7, home-5) dep(Mama-7, to-6) advmod(bring-3, Mama-7) punct(guess-10, ,-8) nsubj(guess-10, I-9) nsubj(warn-13, I-11) advmod(warn-13, better-12) ccomp(guess-10, warn-13) dobj(warn-13, ya-14) punct(guess-10, ;-15) nsubj(feels-17, She-16) parataxis(guess-10, feels-17) det(heartache-19, every-18) dobj(feels-17, heartache-19) nsubj(go-21, I-20) acl:relcl(heartache-19, go-21) nmod(go-21, through-22) punct(guess-10, .-23)

Extracted the following NER entity mentions: She PERSON

Sentence #18 (29 tokens, sentiment: Negative): And if my dad sees me crying, He’ll pour some whiskey over ice, And, tell a lie and say he never really liked you.

Tokens: [Text=And CharacterOffsetBegin=1302 CharacterOffsetEnd=1305 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=if CharacterOffsetBegin=1306 CharacterOffsetEnd=1308 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=my CharacterOffsetBegin=1309 CharacterOffsetEnd=1311 PartOfSpeech=PRP$ Lemma=my NamedEntityTag=O SentimentClass=Neutral] [Text=dad CharacterOffsetBegin=1312 CharacterOffsetEnd=1315 PartOfSpeech=NN Lemma=dad NamedEntityTag=O SentimentClass=Neutral] [Text=sees CharacterOffsetBegin=1316 CharacterOffsetEnd=1320 PartOfSpeech=VBZ Lemma=see NamedEntityTag=O SentimentClass=Neutral] [Text=me CharacterOffsetBegin=1321 CharacterOffsetEnd=1323 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Positive] [Text=crying CharacterOffsetBegin=1324 CharacterOffsetEnd=1330 PartOfSpeech=VBG Lemma=cry NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1330 CharacterOffsetEnd=1331 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=He CharacterOffsetBegin=1332 CharacterOffsetEnd=1334 PartOfSpeech=PRP Lemma=he NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=1334 CharacterOffsetEnd=1337 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=pour CharacterOffsetBegin=1338 CharacterOffsetEnd=1342 PartOfSpeech=VB Lemma=pour NamedEntityTag=O SentimentClass=Neutral] [Text=some CharacterOffsetBegin=1343 CharacterOffsetEnd=1347 PartOfSpeech=DT Lemma=some NamedEntityTag=O SentimentClass=Neutral] [Text=whiskey CharacterOffsetBegin=1348 CharacterOffsetEnd=1355 PartOfSpeech=NN Lemma=whiskey NamedEntityTag=O SentimentClass=Neutral] [Text=over CharacterOffsetBegin=1356 CharacterOffsetEnd=1360 PartOfSpeech=IN Lemma=over NamedEntityTag=O SentimentClass=Neutral] [Text=ice CharacterOffsetBegin=1361 CharacterOffsetEnd=1364 PartOfSpeech=NN Lemma=ice NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1364 CharacterOffsetEnd=1365 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=And CharacterOffsetBegin=1366 CharacterOffsetEnd=1369 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1369 CharacterOffsetEnd=1370 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=tell CharacterOffsetBegin=1371 CharacterOffsetEnd=1375 PartOfSpeech=VB Lemma=tell NamedEntityTag=O SentimentClass=Neutral] [Text=a CharacterOffsetBegin=1376 CharacterOffsetEnd=1377 PartOfSpeech=DT Lemma=a NamedEntityTag=O SentimentClass=Neutral] [Text=lie CharacterOffsetBegin=1378 CharacterOffsetEnd=1381 PartOfSpeech=NN Lemma=lie NamedEntityTag=O SentimentClass=Negative] [Text=and CharacterOffsetBegin=1382 CharacterOffsetEnd=1385 PartOfSpeech=CC Lemma=and NamedEntityTag=O SentimentClass=Neutral] [Text=say CharacterOffsetBegin=1386 CharacterOffsetEnd=1389 PartOfSpeech=VB Lemma=say NamedEntityTag=O SentimentClass=Neutral] [Text=he CharacterOffsetBegin=1390 CharacterOffsetEnd=1392 PartOfSpeech=PRP Lemma=he NamedEntityTag=O SentimentClass=Neutral] [Text=never CharacterOffsetBegin=1393 CharacterOffsetEnd=1398 PartOfSpeech=RB Lemma=never NamedEntityTag=O SentimentClass=Neutral] [Text=really CharacterOffsetBegin=1399 CharacterOffsetEnd=1405 PartOfSpeech=RB Lemma=really NamedEntityTag=O SentimentClass=Neutral] [Text=liked CharacterOffsetBegin=1406 CharacterOffsetEnd=1411 PartOfSpeech=VBD Lemma=like NamedEntityTag=O SentimentClass=Positive] [Text=you CharacterOffsetBegin=1412 CharacterOffsetEnd=1415 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1415 CharacterOffsetEnd=1416 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (CC And) (SBAR (IN if) (S (NP (PRP$ my) (NN dad)) (VP (VBZ sees) (S (NP (PRP me)) (VP (VBG crying)))))) (, ,) (NP (PRP He)) (VP (MD ’ll) (VP (VB pour) (NP (NP (DT some) (NN whiskey)) (PP (IN over) (NP (NN ice))))))) (, ,) (CC And) (, ,) (S (S (VP (VP (VB tell) (NP (DT a) (NN lie))) (CC and) (VP (VB say) (NP (PRP he)) (ADVP (RB never))))) (ADVP (RB really)) (VP (VBD liked) (NP (PRP you)))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=1 prob=0.450    
(@S sentiment=1 prob=0.352 (@S sentiment=1 prob=0.603
(@S sentiment=1 prob=0.710 (@S sentiment=1 prob=0.542
(S sentiment=1 prob=0.594 (CC sentiment=2 prob=0.999 And)
(@S sentiment=1 prob=0.517 (SBAR sentiment=2 prob=0.761
(IN sentiment=2 prob=0.986 if) (S sentiment=2 prob=0.700
(NP sentiment=2 prob=0.920 (PRP$ sentiment=2 prob=0.998 my)
(NN sentiment=2 prob=0.963 dad)) (VP sentiment=2 prob=0.827
(VBZ sentiment=2 prob=0.995 sees) (S sentiment=2 prob=0.544
(NP sentiment=3 prob=0.946 me) (VP sentiment=2 prob=0.631 crying)))))
(@S sentiment=2 prob=0.667 (, sentiment=2 prob=0.997 ,)
(@S sentiment=2 prob=0.482 (NP sentiment=2 prob=0.996 He)
(VP sentiment=2 prob=0.897 (MD sentiment=2 prob=0.998 ’ll)
(VP sentiment=2 prob=0.774 (VB sentiment=2 prob=0.917 pour)
(NP sentiment=2 prob=0.595 (NP sentiment=2 prob=0.739
(DT sentiment=2 prob=0.996 some) (NN sentiment=2 prob=0.631 whiskey))
(PP sentiment=2 prob=0.986 (IN sentiment=2 prob=0.991 over)
(NP sentiment=2 prob=0.982 ice))))))))) (, sentiment=2 prob=0.997 ,))
(CC sentiment=2 prob=0.999 And)) (, sentiment=2 prob=0.997 ,))
(S sentiment=3 prob=0.557 (S sentiment=2 prob=0.748
(@VP sentiment=2 prob=0.829 (VP sentiment=2 prob=0.747
(VB sentiment=2 prob=0.993 tell) (NP sentiment=2 prob=0.725
(DT sentiment=2 prob=0.990 a) (NN sentiment=1 prob=0.870 lie)))
(CC sentiment=2 prob=0.996 and)) (VP sentiment=2 prob=0.947
(@VP sentiment=2 prob=0.932 (VB sentiment=2 prob=0.991 say)
(NP sentiment=2 prob=0.993 he)) (ADVP sentiment=2 prob=0.990 never)))
(@S sentiment=3 prob=0.710 (ADVP sentiment=2 prob=0.994 really)
(VP sentiment=3 prob=0.769 (VBD sentiment=3 prob=0.893 liked)
(NP sentiment=2 prob=0.995 you))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, pour-11) cc(pour-11, And-1) mark(sees-5, if-2) nmod:poss(dad-4, my-3) nsubj(sees-5, dad-4) advcl:if(pour-11, sees-5) nsubj(crying-7, me-6) dep(sees-5, crying-7) punct(pour-11, ,-8) nsubj(pour-11, He-9) aux(pour-11, ’ll-10) det(whiskey-13, some-12) dobj(pour-11, whiskey-13) case(ice-15, over-14) nmod:over(whiskey-13, ice-15) punct(pour-11, ,-16) cc(pour-11, And-17) punct(pour-11, ,-18) csubj(liked-27, tell-19) det(lie-21, a-20) dobj(tell-19, lie-21) cc(tell-19, and-22) conj:and(tell-19, say-23) csubj(liked-27, say-23) dobj(say-23, he-24) neg(say-23, never-25) advmod(liked-27, really-26) conj:and(pour-11, liked-27) dobj(liked-27, you-28) punct(pour-11, .-29)

Extracted the following NER entity mentions: He PERSON he PERSON

Sentence #19 (20 tokens, sentiment: Positive): If we break up, I’ll be fine; But you’ll be breaking more hearts than mine.

Tokens: [Text=If CharacterOffsetBegin=1417 CharacterOffsetEnd=1419 PartOfSpeech=IN Lemma=if NamedEntityTag=O SentimentClass=Neutral] [Text=we CharacterOffsetBegin=1420 CharacterOffsetEnd=1422 PartOfSpeech=PRP Lemma=we NamedEntityTag=O SentimentClass=Neutral] [Text=break CharacterOffsetBegin=1423 CharacterOffsetEnd=1428 PartOfSpeech=VBP Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=up CharacterOffsetBegin=1429 CharacterOffsetEnd=1431 PartOfSpeech=RP Lemma=up NamedEntityTag=O SentimentClass=Neutral] [Text=, CharacterOffsetBegin=1431 CharacterOffsetEnd=1432 PartOfSpeech=, Lemma=, NamedEntityTag=O SentimentClass=Neutral] [Text=I CharacterOffsetBegin=1433 CharacterOffsetEnd=1434 PartOfSpeech=PRP Lemma=I NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=1434 CharacterOffsetEnd=1437 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=1438 CharacterOffsetEnd=1440 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=fine CharacterOffsetBegin=1441 CharacterOffsetEnd=1445 PartOfSpeech=JJ Lemma=fine NamedEntityTag=O SentimentClass=Positive] [Text=; CharacterOffsetBegin=1445 CharacterOffsetEnd=1446 PartOfSpeech=: Lemma=; NamedEntityTag=O SentimentClass=Neutral] [Text=But CharacterOffsetBegin=1447 CharacterOffsetEnd=1450 PartOfSpeech=CC Lemma=but NamedEntityTag=O SentimentClass=Neutral] [Text=you CharacterOffsetBegin=1451 CharacterOffsetEnd=1454 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=1454 CharacterOffsetEnd=1457 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=1458 CharacterOffsetEnd=1460 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=breaking CharacterOffsetBegin=1461 CharacterOffsetEnd=1469 PartOfSpeech=VBG Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=more CharacterOffsetBegin=1470 CharacterOffsetEnd=1474 PartOfSpeech=JJR Lemma=more NamedEntityTag=O SentimentClass=Neutral] [Text=hearts CharacterOffsetBegin=1475 CharacterOffsetEnd=1481 PartOfSpeech=NNS Lemma=heart NamedEntityTag=O SentimentClass=Positive] [Text=than CharacterOffsetBegin=1482 CharacterOffsetEnd=1486 PartOfSpeech=IN Lemma=than NamedEntityTag=O SentimentClass=Neutral] [Text=mine CharacterOffsetBegin=1487 CharacterOffsetEnd=1491 PartOfSpeech=NN Lemma=mine NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1491 CharacterOffsetEnd=1492 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (S (SBAR (IN If) (S (NP (PRP we)) (VP (VBP break) (PRT (RP up))))) (, ,) (NP (PRP I)) (VP (MD ’ll) (VP (VB be) (ADJP (JJ fine))))) (: ;) (CC But) (S (NP (PRP you)) (VP (MD ’ll) (VP (VB be) (VP (VBG breaking) (NP (JJR more) (NNS hearts)) (PP (IN than) (NP (NN mine))))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=3 prob=0.774    
(@S sentiment=3 prob=0.711 (@S sentiment=3 prob=0.746
(@S sentiment=3 prob=0.683 (S sentiment=3 prob=0.720
(SBAR sentiment=2 prob=0.908 (IN sentiment=2 prob=0.997 If)
(S sentiment=2 prob=0.853 (NP sentiment=2 prob=0.996 we)
(VP sentiment=2 prob=0.853 (VBP sentiment=2 prob=0.984 break)
(PRT sentiment=2 prob=0.997 up)))) (@S sentiment=3 prob=0.610
(, sentiment=2 prob=0.997 ,) (@S sentiment=3 prob=0.716
(NP sentiment=2 prob=0.996 I) (VP sentiment=3 prob=0.615
(MD sentiment=2 prob=0.998 ’ll) (VP sentiment=2 prob=0.609
(VB sentiment=2 prob=0.994 be) (ADJP sentiment=3 prob=0.894 fine))))))
(: sentiment=2 prob=0.997 ;)) (CC sentiment=2 prob=0.999 But))
(S sentiment=3 prob=0.412 (NP sentiment=2 prob=0.995 you)
(VP sentiment=2 prob=0.552 (MD sentiment=2 prob=0.998 ’ll)
(VP sentiment=2 prob=0.583 (VB sentiment=2 prob=0.994 be)
(VP sentiment=2 prob=0.463 (@VP sentiment=3 prob=0.456
(VBG sentiment=2 prob=0.962 breaking) (NP sentiment=2 prob=0.866
(JJR sentiment=2 prob=0.992 more) (NNS sentiment=3 prob=0.921 hearts)))
(PP sentiment=2 prob=0.982 (IN sentiment=2 prob=0.998 than)
(NP sentiment=2 prob=0.941 mine))))))) (. sentiment=2 prob=0.997 .))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, fine-9) mark(break-3, If-1) nsubj(break-3, we-2) advcl:if(fine-9, break-3) compound:prt(break-3, up-4) punct(fine-9, ,-5) nsubj(fine-9, I-6) aux(fine-9, ’ll-7) cop(fine-9, be-8) punct(fine-9, ;-10) cc(fine-9, But-11) nsubj(breaking-15, you-12) aux(breaking-15, ’ll-13) aux(breaking-15, be-14) conj:but(fine-9, breaking-15) amod(hearts-17, more-16) dobj(breaking-15, hearts-17) case(mine-19, than-18) nmod:than(breaking-15, mine-19) punct(fine-9, .-20)

Extracted the following NER entity mentions:

Sentence #20 (9 tokens, sentiment: Neutral): You’ll be breaking more hearts than mine.

Tokens: [Text=You CharacterOffsetBegin=1493 CharacterOffsetEnd=1496 PartOfSpeech=PRP Lemma=you NamedEntityTag=O SentimentClass=Neutral] [Text=’ll CharacterOffsetBegin=1496 CharacterOffsetEnd=1499 PartOfSpeech=MD Lemma=will NamedEntityTag=O SentimentClass=Neutral] [Text=be CharacterOffsetBegin=1500 CharacterOffsetEnd=1502 PartOfSpeech=VB Lemma=be NamedEntityTag=O SentimentClass=Neutral] [Text=breaking CharacterOffsetBegin=1503 CharacterOffsetEnd=1511 PartOfSpeech=VBG Lemma=break NamedEntityTag=O SentimentClass=Neutral] [Text=more CharacterOffsetBegin=1512 CharacterOffsetEnd=1516 PartOfSpeech=JJR Lemma=more NamedEntityTag=O SentimentClass=Neutral] [Text=hearts CharacterOffsetBegin=1517 CharacterOffsetEnd=1523 PartOfSpeech=NNS Lemma=heart NamedEntityTag=O SentimentClass=Positive] [Text=than CharacterOffsetBegin=1524 CharacterOffsetEnd=1528 PartOfSpeech=IN Lemma=than NamedEntityTag=O SentimentClass=Neutral] [Text=mine CharacterOffsetBegin=1529 CharacterOffsetEnd=1533 PartOfSpeech=NN Lemma=mine NamedEntityTag=O SentimentClass=Neutral] [Text=. CharacterOffsetBegin=1533 CharacterOffsetEnd=1534 PartOfSpeech=. Lemma=. NamedEntityTag=O SentimentClass=Neutral]

Constituency parse: (ROOT (S (NP (PRP You)) (VP (MD ’ll) (VP (VB be) (VP (VBG breaking) (NP (JJR more) (NNS hearts)) (PP (IN than) (NP (NN mine)))))) (. .)))

Sentiment-annotated binary tree: (ROOT sentiment=2 prob=0.446    
(NP sentiment=2 prob=0.996 You) (@S sentiment=2 prob=0.426
(VP sentiment=2 prob=0.552 (MD sentiment=2 prob=0.998 ’ll)
(VP sentiment=2 prob=0.583 (VB sentiment=2 prob=0.994 be)
(VP sentiment=2 prob=0.463 (@VP sentiment=3 prob=0.456
(VBG sentiment=2 prob=0.962 breaking) (NP sentiment=2 prob=0.866
(JJR sentiment=2 prob=0.992 more) (NNS sentiment=3 prob=0.921 hearts)))
(PP sentiment=2 prob=0.982 (IN sentiment=2 prob=0.998 than)
(NP sentiment=2 prob=0.941 mine))))) (. sentiment=2 prob=0.997 .)))

Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, breaking-4) nsubj(breaking-4, You-1) aux(breaking-4, ’ll-2) aux(breaking-4, be-3) amod(hearts-6, more-5) dobj(breaking-4, hearts-6) case(mine-8, than-7) nmod:than(breaking-4, mine-8) punct(breaking-4, .-9)

Extracted the following NER entity mentions:

But as you can probably tell, the wrapper seems to have been spot on in regards to its accuracy against Sentimentr.

How you read this, is by first concentrating on the lines which start with Sentence #1 (12 tokens, sentiment: Negative): I can’t wait to show you where I grew up.. Telling from the “Document ID”, there should be 20 of these: Document: ID=More-Hearts-1.txt (20 sentences, 370 tokens). Accordingly, you’ve seen Sentence #1 as I have just shown you; following are: sentence #2 Sentence #2 (10 tokens, sentiment: Positive): Walk you ’round the foothills of my town. and sentence #3 Sentence #3 (25 tokens, sentiment: Negative): Probably feel like you’ve been there before, After hearing all the stories; I’ve been telling you For six months now. etc.

Each word in a sentence is a token. The blocks of text following the sentence ID’s Sentence #1... etc, are showing the dependency relations among the tokens in each sentence.[2]

For instance, consider the following:

Dependencies References

  1. More Hearts Than Mine by Ingrid Andress | Billboard The Hot 100 Chart. (2019). /charts/hot-100/2020-03-14
  2. Sliwa, P. (2012). In Defense of Moral Testimony. Philosophical Studies, 158(2), 175–195. https://doi.org/10.1007/s11098-012-9887-6
  3. Kiritchenko, S., & Mohammad, S. M. Happy Accident: A Sentiment Composition Lexicon for Opposing Polarity Phrases. 8.
  4. Kiritchenko, S., Zhu, X., & Mohammad, S. M. (2014). Sentiment Analysis of Short Informal Texts. Journal of Artificial Intelligence Research (JAIR), 50, 723–762.
  5. Kiritchenko, S., Zhu, X., & Mohammad, S. M. (2014). Sentiment Analysis of Short Informal Texts. Journal of Artificial Intelligence Research, 50, 723–762. https://doi.org/10.1613/jair.4272
  6. Kiritchenko, S., & Mohammad, S. (2016). The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition. Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 43–52. https://doi.org/10.18653/v1/W16-0410
  7. Kiritchenko, S., & Mohammad, S. M. (2016). Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best–Worst Scaling. Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL).
  8. Kiritchenko, S., & Mohammad, S. M. (2016). The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition. Proceedings of the Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA).
  9. Kiritchenko, S., & Mohammad, S. M. (2016). Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best–Worst Scaling. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 811–817. https://doi.org/10.18653/v1/N16-1095
  10. Kiritchenko, S., Mohammad, S. M., & Salameh, M. (2016, June). Semeval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases. Proceedings of the International Workshop on Semantic Evaluation.
  11. Kiritchenko, S., Mohammad, S., & Salameh, M. (2016). SemEval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), 42–51. https://doi.org/10.18653/v1/S16-1004
  12. Kiritchenko, S., & Mohammad, S. M. (2016). Sentiment Composition of Words with Opposing Polarities. Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), San Diego, California.
  13. Kiritchenko, S., & Mohammad, S. M. (2016). Sentiment Composition of Words with Opposing Polarities. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1102–1108. https://doi.org/10.18653/v1/N16-1128
  14. Kiritchenko, S., & Mohammad, S. M. (2016). Happy Accident: A Sentiment Composition Lexicon for Opposing Polarity Phrases. Proceedings of 10th Edition of the the Language Resources and Evaluation Conference (LREC).
  15. Kiritchenko, S., Mohammad, S. M., & Salameh, M. (2016, June). Semeval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases. Proceedings of the International Workshop on Semantic Evaluation.
  16. Kiritchenko, S., Mohammad, S., & Salameh, M. (2016). SemEval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), 42–51. https://doi.org/10.18653/v1/S16-1004
  17. Mohammad, S. M., & Turney, P. D. Emotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon. 9.
  18. Mohammad, S. M., & Turney, P. D. (2013). Crowdsourcing a Word-Emotion Association Lexicon. Computational Intelligence, 29(3), 436–465.
  19. Mohammad, S. M. (2018). Word Affect Intensities. Proceedings of the 11th Edition of the Language Resources and Evaluation Conference (LREC-2018).
  20. Mohammad, S. (2018). Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 174–184. https://doi.org/10.18653/v1/P18-1017
  21. Mohammad, S. M. (2018). Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words. Proceedings of the Annual Conference of the Association for Computational Linguistics (ACL).
  22. Mohammad, S. M. (2021). Sentiment Analysis: Automatically Detecting Valence, Emotions, and Other Affectual States from Text. http://arxiv.org/abs/2005.11882
  23. Rinker, T., Dame, U. of N., Technologies, D. of K., Unicode, Inc, Higgins, J., Ward, G., Possel, H., Mechura, M. B., Liu, B., Hu, M., Mohammad, S. M., Turney, P., Cambria, E., Poria, S., Bajpai, R., Schuller, B., SentiWordNet, Wu, L., … Malaescu, I. (2019). Lexicon: Lexicons for Text Analysis (Version 1.2.1). https://CRAN.R-project.org/package=lexicon
  24. Rosenthal, S., Nakov, P., Kiritchenko, S., Mohammad, S. M., Ritter, A., & Stoyanov, V. SemEval-2015 Task 10: Sentiment Analysis in Twitter. 13.
  25. Rosenthal, S., Nakov, P., Kiritchenko, S., Mohammad, S., Ritter, A., & Stoyanov, V. (2015). SemEval-2015 Task 10: Sentiment Analysis in Twitter. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), 451–463. http://www.aclweb.org/anthology/S15-2078
  26. Hopp, F. R., Fisher, J. T., Cornell, D., Huskey, R., & Weber, R. (2021). The Extended Moral Foundations Dictionary (eMFD): Development and Applications of a Crowd-Sourced Approach to Extracting Moral Intuitions from Text. Behavior Research Methods, 53(1), 232–246. https://doi.org/10.3758/s13428-020-01433-0
  27. Graham, J., Nosek, B. A., Haidt, J., Iyer, R., Koleva, S., & Ditto, P. H. (2011). Mapping the Moral Domain. Journal of Personality and Social Psychology, 101(2), 366–385. https://doi.org/10.1037/a0021847
  1. It seems that the valence shifters Sentimentr uses does not recognize “pretend” as one of those. This would certainly be an easy fix if I knew how.

  2. An excellent wrapper for this bit is spacyr. What it does it parse out each of these relations in an easier to read manner.