Reproduce “SEER: Semantic Enhancement and Emotional Reasoning Network for Multimodal Fake News Detection” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Peican Zhu, Yubo Jing, Le Cheng, Bin Chen, Xiaodong Cui, Lianwei Wu, Keke Tang
SEER detects fake news by enriching text-and-image representations with generated image captions and emotion signals from post text and captions. It combines multimodal features with a separate emotion module that models an assumed relationship between emotion and authenticity. On Twitter, SEER reports 0.931 accuracy versus 0.906 for CCGN, but not across every metric on these datasets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.