Dynamic Analysis and Adaptive Discriminator for Fake News Detection

In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection methods can generally be classified into knowledge-based and semanticbased approaches. However, these methods are heavily rely on human expertise and feedback, lacking flexibility. To address this challenge, we propose a Dynamic Analysis and Adaptive Discriminator (DAAD) approach for fake news detection. For knowledge-based methods, we introduce the Monte Carlo Tree Search algorithm to leverage the self-reflective capabilities of large language models (LLMs) for prompt optimization, providing richer, domain-specific details and guidance to the LLMs, while enabling more flexible integration of LLM comment on news content. For semantic-based methods, we define four typical deceit patterns: emotional exaggeration, logical inconsistency, image manipulation, and semantic inconsistency, to reveal the mechanisms behind fake news creation. To detect these patterns, we carefully design four discriminators and expand them in depth and breadth, using the soft-routing mechanism to explore optimal detection models. Experimental results on three real-world datasets demonstrate the superiority of our approach. The codes will be released.

Verdict: True. Reason: The text describes a riot in Longxu Town, Guangxi, detailing overturned police cars and the use of petrol bombs. It includes specific location and time, enhancing its credibility. (Translated from chinese) Verdict: False. Reason: The news headline and content are overly dramatic, using phrases like "looked like Afghanistan" and "explosive scene." It lacks specific news sources and detailed event descriptions, suggesting it may be fake news or exaggerated social media content. (Translated from chinese)