Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation
This addresses the issue of underutilized fact-checking sites in combating fake news on platforms like Twitter and Facebook, representing an incremental improvement in recommendation systems.
The paper tackles the problem of fake news dissemination on social media by proposing a deep-learning based fact-checking URL recommender system, which outperforms eight state-of-the-art models by at least 3-5.3% in experiments on a real-world dataset.
To combat fake news, researchers mostly focused on detecting fake news and journalists built and maintained fact-checking sites (e.g., Snopes.com and Politifact.com). However, fake news dissemination has been greatly promoted via social media sites, and these fact-checking sites have not been fully utilized. To overcome these problems and complement existing methods against fake news, in this paper we propose a deep-learning based fact-checking URL recommender system to mitigate impact of fake news in social media sites such as Twitter and Facebook. In particular, our proposed framework consists of a multi-relational attentive module and a heterogeneous graph attention network to learn complex/semantic relationship between user-URL pairs, user-user pairs, and URL-URL pairs. Extensive experiments on a real-world dataset show that our proposed framework outperforms eight state-of-the-art recommendation models, achieving at least 3~5.3% improvement.