Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media
CoRR(2024)
Abstract
With the rapid development of social media, the wide dissemination of fake
news on social media is increasingly threatening both individuals and society.
In the dynamic landscape of social media, fake news detection aims to develop a
model trained on news reporting past events. The objective is to predict and
identify fake news about future events, which often relate to subjects entirely
different from those in the past. However, existing fake detection methods
exhibit a lack of robustness and cannot generalize to unseen events. To address
this, we introduce Future ADaptive Event-based Fake news Detection (FADE)
framework. Specifically, we train a target predictor through an adaptive
augmentation strategy and graph contrastive learning to make more robust
overall predictions. Simultaneously, we independently train an event-only
predictor to obtain biased predictions. Then we further mitigate event bias by
obtaining the final prediction by subtracting the output of the event-only
predictor from the output of the target predictor. Encouraging results from
experiments designed to emulate real-world social media conditions validate the
effectiveness of our method in comparison to existing state-of-the-art
approaches.
MoreTranslated text
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined