news tweets 0.00268061
ranking tweets 0.001972329
related tweets 0.001934047
informative tweets 0.0018950809999999998
redundant tweets 0.001829768
tweets state 0.001811417
dant tweets 0.001810635
noisy tweets 0.001807378
tory tweets 0.001807378
user information 0.001784818
content features 0.00177371
same news 0.001639466
different information 0.001606512
tweets 0.00160261
similarity features 0.001579138
first tweet 0.001574935
same information 0.001552308
other feature 0.001541925
tweet language 0.001512612
content feature 0.0014943729999999998
tweet pairs 0.0014117469999999999
content model 0.001410937
news articles 0.00139785
news web 0.001386379
tweet pair 0.001382169
tweet redundancy 0.001377777
information redundancy 0.001347099
news article 0.001332138
factual news 0.0013242879999999999
social content 0.001298035
news item 0.001283057
redundant tweet 0.001248678
tweet sets 0.0012445619999999998
following feature 0.001239618
twitter search 0.001239225
twitter language 0.00121688
information need 0.001213506
syntactic feature 0.001203837
information redun 0.001200082
information rel 0.00119777
social media 0.0011860730000000002
other users 0.001175943
baseline model 0.001135102
feature space 0.001129268
features 0.00112714
single feature 0.00112343
content analysis 0.00112291
detection dataset 0.0011185869999999999
large set 0.001111765
different models 0.0011090919999999999
twitter results 0.0011067590000000001
different topic 0.0011005400000000001
learning system 0.001096549
lexical content 0.001096179
this feature 0.0010924519999999998
feature spaces 0.0010762229999999998
initial user 0.001075032
feature combinations 0.001071248
tent feature 0.0010689229999999998
user query 0.001065575
test set 0.001064718
lex feature 0.001063069
many words 0.001061677
above feature 0.0010590579999999999
linguistic content 0.00105825
feature combina 0.001052636
same topic 0.0010463360000000001
learning models 0.0010425909999999998
detection task 0.00104137
detection models 0.00103235
same time 0.0010256500000000001
twitter corpus 0.001024668
tweet 0.00102152
model bow 0.0010177909999999999
first time 0.001017599
learning algorithm 0.001015653
text similarity 0.0010085530000000001
synt model 0.001007527
pair content 0.001007219
training set 0.001006293
word vector 0.001005036
wbow model 0.001003102
syntactic content 0.001002604
model aroc 9.98532E-4
twitter community 9.95459E-4
information 9.90842E-4
word similarity 9.86895E-4
actual twitter 9.831969999999999E-4
twitter stream 9.83009E-4
other types 9.79721E-4
lex model 9.79633E-4
accurate twitter 9.78836E-4
probabilistic model 9.69802E-4
twitter conversations 9.49718E-4
rule content 9.42926E-4
negative pairs 9.360359999999999E-4
large number 9.20588E-4
different systems 9.189090000000001E-4
different con 9.16232E-4
final set 9.122819999999999E-4
