Fake News Feels Different: How SEER Uses Emotion and Semantics to Spot Deception
TL;DR for operators SEER is not a “sentiment detector for lies.” That would be wonderfully simple and operationally disastrous. It is a multimodal fake-news detection architecture that first tries to make images more semantically usable, then adds emotion as a probabilistic auxiliary signal rather than a moral verdict. The practical workflow is easy to understand: generate a caption for the image, align the text-image relationship using CLIP-style representations, fuse text, image, and caption features through attention, then use an expert emotional reasoning module to learn how emotional tone correlates with authenticity in the dataset. The paper reports accuracy of 0.929 on Weibo and 0.931 on Twitter, outperforming the tested baselines.1 ...