Towards Fine-Grained Reasoning for Fake News Detection
This work addresses the problem of detecting fake news, which is critical for media consumers and platforms, by proposing an incremental improvement through a novel method for incorporating human knowledge and modeling evidence differences.
The paper tackles fake news detection by developing a fine-grained reasoning framework that mimics human logical processes and models subtle word-level clues, resulting in a model that outperforms state-of-the-art methods and demonstrates explainability.
The detection of fake news often requires sophisticated reasoning skills, such as logically combining information by considering word-level subtle clues. In this paper, we move towards fine-grained reasoning for fake news detection by better reflecting the logical processes of human thinking and enabling the modeling of subtle clues. In particular, we propose a fine-grained reasoning framework by following the human information-processing model, introduce a mutual-reinforcement-based method for incorporating human knowledge about which evidence is more important, and design a prior-aware bi-channel kernel graph network to model subtle differences between pieces of evidence. Extensive experiments show that our model outperforms the state-of-the-art methods and demonstrate the explainability of our approach.