Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News
Published in ACM Journal of Data and Information Quality, 11(3), 2019
Luís Borges, Bruno Martins, and Pável Calado
This work combines recurrent neural representations with text similarity features to identify whether a news article agrees with, disagrees with, discusses, or is unrelated to a headline. It also studies transfer learning from natural language inference datasets, evaluating the approach on the Fake News Challenge stance detection task.