Rumor detection in social network based on user, content and lexical features

A survey on rumor detection and prevention in social media using deep learning

In the current digital era, massive amounts of unreliable, purposefully misleading material, such as texts and images, are being shared widely on various web platforms to deceive the reader. Most of us use social media sites to exchange or obtain information. This opens a lot of space for false information, like fake news, rumors, etc., to spread that could harm a society's social fabric, a person's reputation, or the legitimacy of a whole country. Therefore, preventing the transmission of such dangerous material across platforms is a digital priority. However, the main goal of this survey paper is to thoroughly examine several current state-of-the-art research works on rumor control (detection and prevention) that use deep learning-based techniques and to identify major distinctions between these research efforts. The comparison results are intended to identify research gaps and challenges for rumor detection, tracking, and combating. This survey of the literature makes a significant contribution by highlighting several cutting-edge deep learning-based models for rumor detection in social media and critically evaluating their effectiveness on recently available standard datasets. Furthermore, to have a thorough grasp of rumor prevention to spread, we also looked into various pertinent approaches, including rumor veracity classification, stance classification, tracking, and combating. We also have created a summary of recent datasets with all the necessary information and analysis. Finally, as part of this survey, we have identified some of the potential research gaps and challenges that need to be addressed in order to develop early, effective methods of rumor control.

KG-MFEND: an efficient knowledge graph-based model for multi-domain fake news detection

The widespread dissemination of fake news on social media brings adverse effects on the public and social development. Most existing techniques are limited to a single domain (e.g., medicine or politics) to identify fake news. However, many differences exist commonly across domains, such as word usage, which lead to those methods performing poorly in other domains. In the real world, social media releases millions of news pieces in diverse domains every day. Therefore, it is of significant practical importance to propose a fake news detection model that can be applied to multiple domains. In this paper, we propose a novel framework based on knowledge graphs (KG) for multi-domain fake news detection, named KG-MFEND. The model's performance is enhanced by improving the BERT and integrating external knowledge to alleviate domain differences at the word level. Specifically, we construct a new KG that encompasses multi-domain knowledge and injects entity triples to build a sentence tree to enrich the news background knowledge. To solve the problem of embedding space and knowledge noise, we use the soft position and visible matrix in knowledge embedding. To reduce the influence of label noise, we add label smoothing to the training. Extensive experiments are conducted on real Chinese datasets. And the results show that KG-MFEND has a strong generalization capability in single, mixed, and multiple domains and outperforms the current state-of-the-art methods for multi-domain fake news detection.