False news detection system and method based on evidence perception hierarchical interaction attention network

Abstract

The invention discloses a false news detection system and method based on an evidence perception hierarchical interaction attention network, which discusses more credible evidence semantics by capturing evidence fragments and fusing source credibility, and is used for discovering suspicious parts in false news so as to carry out interpretable false news detection. According to the method, suspicious parts in claim settlement can be captured, more credible evidence semantics can be explored for the parts, and the interpretability of false news detection is enhanced; the internal interaction module composed of self-attention and symmetric attention enhances deep interaction and matching between news semantics and related articles, so that key evidence fragments can be effectively obtained; the global reasoning module not only can obtain more credible evidences from key evidence fragments through gating affine transformation, but also can relieve the influence of extreme semantics on a detection result through global interactive reasoning.

Description

【Technical field】 [0001] The invention belongs to the field of electronic information technology, and relates to a fake news detection system and method based on evidence perception layered interactive attention network. 【Background technique】 [0002] In recent years, new media represented by the Internet has been rapidly developed and widely popularized. Social media, which is uniquely characterized by user-generated content, has become the main channel for network information release, dissemination, sharing and consumption. Due to the low cost of information generation and dissemination and the lack of immediate supervision, social media has also become a place where false information, including hoaxes, rumors, and fake news, floods. Science research shows that fake news in social media accounts for almost 6% of all news consumption. In addition, since the 2016 U.S. election, the ravages of fake news have caused the traditional media in Europe and the United States to lo...

AI Technical Summary

Problems solved by technology

However, current evidence-based interpretable fake news detection still has some general flaws: 1) They extract the whole sequence or salient words as evidence, it is hard to focus on the problematic false parts of fake news, and it is difficult to provide a Accurate and effective explanations to debunk the final verification results; 2) They use news related articles indiscriminately, ignoring the source credibility of these articles, which may cause noise characteristics of some unreliable articles to interfere with experimental results

Images