BaitWatcher: A lightweight web interface for the detection of incongruent news headlines
This addresses the issue of online misinformation for news readers by providing a tool to detect misleading headlines, though it is incremental as it builds on existing methods for text analysis.
The study tackled the problem of incongruent news headlines, where headlines misrepresent article contents, by developing BaitWatcher, a lightweight web interface that uses a hierarchical recurrent encoder to estimate incongruence likelihood, achieving results based on a million-scale dataset and focus group feedback.
In digital environments where substantial amounts of information are shared online, news headlines play essential roles in the selection and diffusion of news articles. Some news articles attract audience attention by showing exaggerated or misleading headlines. This study addresses the \textit{headline incongruity} problem, in which a news headline makes claims that are either unrelated or opposite to the contents of the corresponding article. We present \textit{BaitWatcher}, which is a lightweight web interface that guides readers in estimating the likelihood of incongruence in news articles before clicking on the headlines. BaitWatcher utilizes a hierarchical recurrent encoder that efficiently learns complex textual representations of a news headline and its associated body text. For training the model, we construct a million scale dataset of news articles, which we also release for broader research use. Based on the results of a focus group interview, we discuss the importance of developing an interpretable AI agent for the design of a better interface for mitigating the effects of online misinformation.