sentiment analysis 0.004479388
sentiment label 0.004214402
sentiment transition 0.004205121
sentiment distribution 0.0042019810000000005
basic sentiment 0.004191798
microblog sentiment 0.00417333
sentiment presentation 0.004164095
sentiment labels 0.004154478
sentiment detection 0.004112453
sentiment recognition 0.004107242
sentiment dis 0.004100986
contextual sentiment 0.004091621
sentiment distribu 0.004088395
sentiment distributions 0.004087294
original sentiment 0.004083583
adjusted sentiment 0.004066523
sentiment transi 0.004065548
sentiment recogni 0.004064935
sentiment detector 0.004064935
sentiment 0.00383483
classification model 0.001751727
model approach 0.001701831
word patterns 0.001673366
language model 0.0016330910000000001
presentation system 0.001464025
generation model 0.001444396
transition model 0.001436821
basic model 0.001423498
system flow 0.0014148960000000001
system perspective 0.001403306
system demo 0.001389884
demonstration system 0.0013804160000000002
memetube system 0.0013672740000000001
emotion model 0.001350667
annotated data 0.0013338479999999999
different classification 0.0013211429999999999
training set 0.001299622
testing data 0.001288388
such information 0.0012756999999999998
negative sentiments 0.0011746039999999999
negative sen 0.0011534
system 0.00113476
score vector 0.00111722
particular topic 0.0011160949999999999
negative valence 0.001094685
negative sense 0.001072076
model 0.00106653
classification methods 0.001035433
training corpus 0.001035004
classifier approach 0.001013809
timent classification 0.001010075
cases svm 0.001001422
such post 0.001001139
different sentiments 9.7302E-4
such probability 9.70126E-4
positive sentiments 9.522109999999999E-4
punctuation information 9.512419999999999E-4
chord set 9.46758E-4
additional information 9.4537E-4
set selection 9.44096E-4
affective score 9.3235E-4
sum approach 9.20247E-4
svm sun 9.162910000000001E-4
svm lewin 9.162910000000001E-4
svm riley 9.162910000000001E-4
svm davidov 9.162910000000001E-4
instant information 9.159929999999999E-4
linguistics features 9.07832E-4
such goal 9.05831E-4
information engineering 9.058269999999999E-4
same classifier 9.02316E-4
friendship information 8.924949999999999E-4
different queries 8.8328E-4
score vectors 8.830159999999999E-4
enough information 8.813569999999999E-4
ship information 8.799579999999999E-4
different kinds 8.7828E-4
such mod 8.7494E-4
affective vector 8.71602E-4
different setups 8.67911E-4
different perspectives 8.67911E-4
other half 8.62025E-4
such generalization 8.5938E-4
words 8.55976E-4
tive vector 8.541339999999999E-4
ing service 8.297630000000001E-4
posts first 8.03086E-4
topic 8.01819E-4
abovementioned language 8.00929E-4
many people 8.00114E-4
music generation 7.963969999999999E-4
first part 7.83133E-4
same way 7.71006E-4
vector anger 7.66002E-4
same period 7.62798E-4
recognition accuracy 7.62687E-4
related work 7.56153E-4
same circumstances 7.558109999999999E-4
tion generation 7.50438E-4
many respects 7.40174E-4
