This research focuses on identifying and analyzing deceptive and untrustworthy content in online media. By leveraging NLP, large language models (LLMs), and syntactic pattern analysis, the study aims to detect manipulative language, misinformation, and hidden biases. The system will not only flag potentially unreliable documents but also provide explanations and warnings to help users understand why a source may be untrustworthy. This approach seeks to enhance digital literacy, mitigate the impact of misinformation, and protect public trust from harmful narratives and online manipulation.

• Hsu, Yi-Shin Chen (2024, Dec). Graph-Based Syntactic Analysis for Cross-Domain Fraud Messages Detection. Proceedings of the 29th International Conference on Technologies and Applications of Artificial Intelligence (TAAI 2024), Hsinchu, Taiwan.
• Huang, TW Liu, SR Lee, FH Calderon Alvarado, YS Chen (2020). Conquering Cross-source Failure for News Credibility: Learning Generalizable Representations beyond Content Embedding. Proceedings of The Web Conference 2020 (TheWeb 2020), 774-784.