such features 0.002565021
other features 0.002406045
syntactic features 0.002292227
many features 0.002286418
feature set 0.002280388
such feature 0.002246041
good features 0.0022004249999999998
specific features 0.002174367
feature selection 0.00216493
grammatical features 0.0021434
unigram features 0.002115221
own features 0.002101681
recognizable features 0.002093166
weak features 0.002085724
tracted features 0.002074605
large feature 0.00197126
possible feature 0.001921222
feature space 0.001895318
features 0.00187349
feature sets 0.001868041
feature engineering 0.001867011
feature vectors 0.0018060300000000001
language model 0.001776799
imperative feature 0.001764682
feature dif 0.001761465
feature search 0.00176025
feature selec 0.001755644
sparse feature 0.001755644
word information 0.001673711
single words 0.001628562
training set 0.001575271
few words 0.00156194
feature 0.00155451
words representation 0.0015098429999999999
training data 0.001493768
text classification 0.001488689
words links 0.001471474
links words 0.001471474
work language 0.001457336
words baselines 0.001443517
words simulta 0.001439425
infrequent words 0.001439425
modeling language 0.0013984709999999999
language models 0.001385844
form word 0.0013621599999999998
word sequences 0.001347518
training texts 0.001310646
test set 0.001303981
word unigrams 0.001268806
word bigrams 0.001265157
model personality 0.001258611
language process 0.0012548149999999998
words 0.00123672
different personal 0.001225119
test data 0.001222478
language use 0.001222318
different types 0.001184125
natural language 0.001180509
previous text 0.001175256
model authors 0.001169161
weighted training 0.00114392
language researcher 0.001124267
different sort 0.001113213
different classes 0.001106616
text sample 0.001102178
classification problem 0.001094371
classification task 0.001093255
downspeak text 0.001087909
upspeak text 0.001085546
different lev 0.0010816530000000001
text classifica 0.001078584
training instances 0.001077997
text samples 0.001069294
pos tag 0.00106788
social information 0.0010624039999999999
traditional text 0.001059722
text partitions 0.0010535969999999999
labeled training 0.001052576
unseen text 0.001052294
narrative text 0.001052294
unbalanced training 0.001050123
personality classification 0.001043208
ing set 0.001041907
power information 0.001030629
tag sequences 0.001025778
analysis work 0.0010173769999999999
set size 0.001017207
learning approach 0.001008691
selection method 0.001000221
overall set 9.76651E-4
binary classification 9.75023E-4
lexical components 9.73473E-4
way classification 9.72695E-4
set instances 9.54482E-4
low information 9.524049999999999E-4
significant work 9.520959999999999E-4
tag unigrams 9.47066E-4
tag bigrams 9.43417E-4
attribution work 9.37912E-4
authorship analysis 9.2708E-4
