Cross-Domain Fake News Detection Through Fusion of Evidence from Multiple Social Media Platforms

Fake news has become a significant challenge on online social platforms, increasing uncertainty and unwanted tension in society. The negative impact of fake news on political processes, public health, and social harmony underscores the urgency of developing more effective detection systems. Existing methods for fake news detection often focus solely on one platform, potentially missing important clues that arise from multiple platforms. Another important consideration is that the domain of fake news changes rapidly, making cross-domain analysis more difficult than in-domain analysis. To address both of these limitations, our method takes evidence from multiple social media platforms, enhances our cross-domain analysis, and improves overall detection accuracy. Our method employs the Dempster–Shafer combination rule for aggregating probabilities for comments being fake from two different social media platforms. Instead of directly using the comments as features, our approach improves fake news detection by examining the relationships and calculating correlations among comments from different platforms. This provides a more comprehensive view of how fake news spreads and how users respond to it. Most importantly, our study reveals that true news is typically rich in content, while fake news tends to generate a vast thread of comments. Therefore, we propose a combined method that merges content- and comment-based approaches, allowing our model to identify fake news with greater accuracy and showing an overall improvement of 7% over previous methods.