Investigating Rumor News Using Agreement-Aware Search
share
In recent years, rumor news has been generated by humans as well as robots in order to attract readership, influence opinions, and increase internet click revenue. Its detrimental effects have become a worldwide phenomenon, leading to confusion over facts and causing mistrust about media reports. However, evaluating the veracity of news stories can be a complex and cumbersome task, even for experts. One of the challenging problems in this context is to automatically understand different points of view, i.e., whether other news articles reporting on the same problem agree or disagree with the reference story. This can then lead to the identification of news articles that propagate false rumors. Here, we propose a novel agreement-aware search framework, Maester, for dealing with the problem of rumor detection. Given an investigative question summarizing some news story or topic, it will retrieve related articles to that question, assign and display top articles from agree, disagree, and discuss categories to users, and thus provide a more holistic view. Our work makes two observations. First, relatedness can commonly be determined by keywords and entities occurred in both questions and articles. Second, the level of agreement between the investigative question and the related news article can often be decided by a few key sentences. Accordingly, we design our approach for relatedness detection to focus on keyword/entity matching using gradient boosting trees, while leveraging recurrent neural networks and posing attentions to key sentences to infer the agreement level. Our evaluation is based on the dataset from the Fake News Challenge (FNC). Extensive experiments demonstrate up to an order of magnitude improvement of Maester over all baseline methods for agreement-aware search as well as slightly improved accuracy based on the same metrics used in FNC.
READ FULL TEXT
