topic model 0.00473539
topic word 0.00465631
topic distribution 0.00431536
topic words 0.004239662999999999
other topic 0.003945573
topic models 0.0038235099999999996
latent topic 0.0037922
new topic 0.0037609849999999997
topic structure 0.0037073899999999996
online topic 0.003643216
single topic 0.0036376869999999997
current topic 0.0036319489999999998
dynamic topic 0.0036301299999999996
topic interests 0.0035754669999999997
specific topic 0.003564693
topic evolution 0.003541132
topic trends 0.003532643
topic trend 0.0035296029999999996
topic tracking 0.003508061
bilistic topic 0.00350498
topic inter 0.003504223
topic examples 0.003500305
topic transitions 0.003500305
biterm topic 0.003500305
topic 0.00328382
word distribution 0.00240403
document model 0.002169895
model inference 0.002008745
new model 0.001928735
word distributions 0.001777679
behavior model 0.0017699539999999998
graphical model 0.0017315319999999998
dynamic word 0.0017188000000000001
background word 0.001711325
model extension 0.0017033259999999998
improved model 0.001679823
tracking model 0.001675811
proved model 0.001672629
word distribu 0.0016537560000000001
other words 0.0016175959999999998
word usage 0.001595639
topical words 0.0015060999999999998
dirichlet distribution 0.001497786
bursty topics 0.001471335
model 0.00145157
top words 0.001372016
time tweets 0.001336077
ity distribution 0.00129966
background words 0.001294678
rate distribution 0.001282214
words low 0.001234172
previous time 0.001218837
stop words 0.001213955
twitter data 0.001211893
words rate 0.0012065169999999998
other models 0.001201443
eral words 0.001190708
multiple topics 0.00117848
basic words 0.00117495
current time 0.001155736
arek topics 0.00115188
new data 0.001146944
time interests 0.001099254
unit time 0.001097189
variable number 0.001091286
time period 0.001087772
next time 0.00108293
single document 0.001072192
time evolution 0.0010649190000000001
time order 0.001061191
data set 0.001059649
latent variable 0.001043239
time sequence 0.001033696
time interval 0.001031796
distribution 0.00103154
time dependency 0.001028379
time stamp 0.001026529
generative document 0.001025519
final data 0.001005267
gibbs sampling 9.87734E-4
latent dirichlet 9.74626E-4
document collections 9.66052E-4
normal document 9.637129999999999E-4
words 9.55843E-4
large number 9.50149E-4
general tweets 9.45971E-4
topics 9.34611E-4
online inference 9.16571E-4
result figure 9.10115E-4
public events 9.08802E-4
latent variables 9.03768E-4
original twitter 9.011889999999999E-4
other hand 8.880079999999999E-4
tweets online 8.87866E-4
other conven 8.79459E-4
new assumption 8.77444E-4
modeling tweets 8.73226E-4
ttm figure 8.730960000000001E-4
latent value 8.714829999999999E-4
twitter users 8.62869E-4
