User stances toward five topics are detected from Twitter network signals (follows, likes, interactions) with accuracy comparable to text-based models, and combining networks with text gives the highest reported F1 on SemEval 2016.
MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We describe MITRE's submission to the SemEval-2016 Task 6, Detecting Stance in Tweets. This effort achieved the top score in Task A on supervised stance detection, producing an average F1 score of 67.8 when assessing whether a tweet author was in favor or against a topic. We employed a recurrent neural network initialized with features learned via distant supervision on two large unlabeled datasets. We trained embeddings of words and phrases with the word2vec skip-gram method, then used those features to learn sentence representations via a hashtag prediction auxiliary task. These sentence vectors were then fine-tuned for stance detection on several hundred labeled examples. The result was a high performing system that used transfer learning to maximize the value of the available training data.
fields
cs.SI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media
User stances toward five topics are detected from Twitter network signals (follows, likes, interactions) with accuracy comparable to text-based models, and combining networks with text gives the highest reported F1 on SemEval 2016.