Stance detection with bidirectional conditional encoding

Stance detection is the task of classifying the attitude expressed in a text towards a target such as "Climate Change is a Real Concern" to be "positive", "negative" or "neutral". Previous work has assumed that either the target is mentioned in the text or that training data for every target is given. This paper considers the more challenging version of this task, where targets are not always mentioned and no training data is available for the test targets. We experiment with conditional LSTM encoding, which builds a representation of the tweet that is dependent on the target, and demonstrate that it outperforms the independent encoding of tweet and target. Performance improves even further when the conditional model is augmented with bidirectional encoding. The method is evaluated on the SemEval 2016 Task 6 Twitter Stance Detection corpus and achieves performance second best only to a system trained on semi-automatically labelled tweets for the test target. When such weak supervision is added, our approach achieves state-of-the-art results.