topic model 0.00440868
topic distribution 0.003969697
document topic 0.003845833
topic models 0.003686795
author topic 0.003353476
popular topic 0.003285753
topic dis 0.003281068
topic sets 0.00326912
topic balance 0.003266802
topic indicator 0.003260351
symmetric topic 0.00325721
disjoint topic 0.003255917
topic ratio 0.003254733
topic settings 0.003248576
topic mod 0.003244545
topic pri 0.003235859
aware topic 0.003235859
topic exchangeability 0.003235859
topic 0.00304514
document words 0.002002523
lda model 0.001986243
document topics 0.001969393
word distributions 0.001854268
word level 0.001824268
other words 0.0017808200000000002
word distribu 0.001734015
word dis 0.0017235080000000001
text words 0.001709907
same topics 0.001696041
word index 0.0016847070000000001
single model 0.0016481170000000002
specific words 0.001582384
model background 0.0015806750000000001
dadt model 0.001561047
dmr model 0.001554452
author words 0.001510166
author topics 0.001477036
vocabulary words 0.001469042
dadt topics 0.001366207
model 0.00136354
corpus distribution 0.00122748
other models 0.001220645
words 0.00120183
topics 0.0011687
document labels 0.001145503
document level 0.001137381
distribution estimates 0.001125331
same time 0.001002572
test text 9.53502E-4
distribution 9.24557E-4
other methods 9.03935E-4
latent dirichlet 8.985219999999999E-4
blog dataset 8.93338E-4
test texts 8.70853E-4
training texts 8.624850000000001E-4
lda component 8.604309999999999E-4
text sampling 8.590010000000001E-4
additional information 8.4332E-4
blog results 8.39856E-4
same author 8.35677E-4
full dataset 8.25328E-4
large text 8.088850000000001E-4
individual documents 8.07479E-4
such elements 8.04276E-4
document 8.00693E-4
other studies 7.832780000000001E-4
other hand 7.74135E-4
same issue 7.66379E-4
text corpora 7.571850000000001E-4
classification accuracy 7.52505E-4
experiment results 7.489580000000001E-4
blog method 7.388830000000001E-4
different priors 7.28943E-4
dirichlet allocation 7.279669999999999E-4
author style 7.22246E-4
traditional problem 7.08E-4
gibbs sampling 7.06083E-4
future work 6.996260000000001E-4
many authors 6.96984E-4
similar style 6.93759E-4
parameter values 6.917749999999999E-4
results belief 6.91578E-4
training subset 6.89527E-4
additional feature 6.86702E-4
stable results 6.80598E-4
generative process 6.78796E-4
cation problem 6.63279E-4
formal texts 6.57975E-4
early work 6.54584E-4
additional svm 6.51603E-4
models 6.41655E-4
training sam 6.38855E-4
random seed 6.38201E-4
anonymous texts 6.381609999999999E-4
attribution methods 6.34233E-4
support vector 6.27643E-4
work directions 6.25786E-4
est work 6.23062E-4
attribution accuracy 6.2195E-4
vector machines 6.20943E-4
