different emotion 0.003709861
emotion data 0.003678292
emotion classification 0.003652339
emotion analysis 0.003442043
emotion ranking 0.003427615
corresponding emotion 0.003412337
pairwise emotion 0.0033997610000000003
reader emotion 0.0033555300000000002
emotion classifiers 0.0033234700000000002
emotion pairs 0.00330866
emotion sequence 0.0033017990000000002
emotion category 0.00330078
emotion list 0.003299917
popular emotion 0.003296744
emotion categories 0.003272433
emotion space 0.003248439
emotion rank 0.00324287
single emotion 0.003224775
emotion ranker 0.003212716
emotion rankers 0.003212716
true emotion 0.003210038
emotion cate 0.003204628
grate emotion 0.003203311
unique emotion 0.003203311
emotion 0.00295407
other words 0.002179556
word features 0.002101153
chinese words 0.0020285290000000003
word sentiment 0.00198569
english words 0.001959233
news training 0.001957833
training news 0.001957833
test news 0.001912874
chinese news 0.0018701289999999999
words bigrams 0.001840152
metadata words 0.001785588
news articles 0.0017152119999999998
chinese word 0.001710509
news categories 0.001687923
news article 0.001686697
news headlines 0.00166143
different features 0.001647004
news metadata 0.001627188
news arti 0.0016224249999999998
news meta 0.0016192899999999998
data features 0.001615435
emotional information 0.0015437720000000001
words 0.00152796
word unigram 0.001490404
word segmentation 0.001483523
nese word 0.001467793
word segmenter 0.001466169
word boundaries 0.001460383
distribution information 0.001424233
different feature 0.001338593
negative sentiment 0.0013252609999999999
emotional distribution 0.001314281
training data 0.001312495
classification results 0.001309698
first feature 0.001301585
different methods 0.001283076
test data 0.001267536
classification performance 0.00126704
features figure 0.001265209
feature value 0.001258178
first approach 0.00121517
same time 0.0011956369999999998
order information 0.001184432
feature values 0.0011838349999999998
bigram features 0.001155311
information retrieval 0.00114481
pairwise classification 0.0011439599999999999
training corpus 0.001142938
other research 0.001141626
emotional probability 0.0011281429999999999
ranking task 0.001121212
feature vector 0.001114859
tional information 0.001099025
test corpus 0.001097979
ranking method 0.001093706
probability value 0.001086609
method average 0.001076551
related work 0.001069031
weight vector 0.0010590209999999998
distribution estimation 0.001049704
emotional dis 0.001046419
similar training 0.0010433500000000002
ranking performance 0.0010423160000000002
classification accuracy 0.001040634
emotional responses 0.001036024
emotional categories 0.001035273
ranking function 0.001031573
estimation performance 0.0010211040000000001
emotional distributions 0.001009822
ranking emotions 0.0010072100000000001
different angle 0.001006953
emotional ambiguity 0.001001638
ranking methods 0.0010008299999999999
classification accuracies 9.95964E-4
small values 9.92013E-4
