Semeval 2016 Task 6: Detecting Stance in Tweets - Results
 Share
The version of the browser you are using is no longer supported. Please upgrade to a supported browser.Dismiss

 
View only
 
 
ABCDEFGHIJKLMNOPQRST
1
Task ATeam NameOfficial MetricTask BTeam NameOfficial Metric
2
Benchmark system by organizers*
0.6910
3
1MITRE0.67821pkudblab0.5628
4
2pkudblab0.67332LitisMind0.4466
5
3TakeLab0.66833INF-UFRGS-OPINION-MINING0.4232
6
4PKULCWM0.65764UWB0.4202
7
5ECNU0.65555ECNU0.3408
8
6CU-GWU Perspective0.63606USFD0.3270
9
6IUCL-RF0.63607Thomson Reuters0.3239
10
8DeepStance0.63548ltl.uni-due0.2614
11
9UWB0.63429NEUSA0.2573
12
10IDI@NTNU0.6247
13
11Tohoku0.6221
14
12ltl.uni-due0.6173
15
13LitisMind0.6144
16
14JU_NLP0.6060
17
15NEUSA0.6012
18
16nldsucsc0.5936
19
17WFU/TNT0.5922
20
18INESC-ID0.5758
21
19Thomson Reuters0.4619
22
23
Official metric: (F_favor + F_against)/2
24
25
*Benchmark Stance Detection System:
26
Many of the same features used in the NRC-Canada system were also used in a benchmark stance-detection system. This system obtained a score of 0.691 in Task A, outperforming submissions from all 19 teams that participated (Mohammad et al., 2017). The highest score on this dataset as of February 2016 is obtained by using that benchmark with word embedding features, obtainng a score of 70.3 (Mohammad et al., 2017). Our stance system is not publicly available yet. However, the AffectiveTweets Package can be used to generate feature vectors similar to those used by us for stance and sentiment.
27
Stance and Sentiment in Tweets. Saif M. Mohammad, Parinaz Sobhani, and Svetlana Kiritchenko. Special Section of the ACM Transactions on Internet Technology on Argumentation in Social Media, 2017, 17(3).
28
Paper (pdf)
BibTeX
29
Other Links:
30
NRC-Canada sentiment system
31
AffectiveTweets Package
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
Loading...
 
 
 
Primary Results
Task A per-target results
Task A Opinion towards target and towards other
Task B Opinion towards target and towards other