Satirical News Detection with Semantic Feature Extraction and Game-theoretic Rough Sets

TL;DR

This work tackles satirical news detection on tweet-length content by combining semantic feature extraction with a three-way decision framework using game-theoretic rough sets (GTRS). It introduces features capturing inconsistencies across noun phrases, clauses, and named entities, plus a TF-IDF-based word indicator, all grounded in Glove embeddings and Flair for syntax/NER. The GTRS classifier derives probabilistic thresholds $(oldsymbol\alpha,\boldsymbol\beta)$ via game equilibrium and repetition learning, producing three decision regions: satirical, legitimate, and deferral. Empirical results on a curated tweet dataset demonstrate that GTRS outperforms Pawlak rough sets and SVM in terms of accuracy and coverage, delivering a high-confidence, interpretable framework for detecting satire with a measured deferral option. The method offers a practical approach for real-world misinformation detection, with potential extensions to document-level features and broader NLP praise of semantic reasoning under uncertainty.

Abstract

Satirical news detection is an important yet challenging task to prevent spread of misinformation. Many feature based and end-to-end neural nets based satirical news detection systems have been proposed and delivered promising results. Existing approaches explore comprehensive word features from satirical news articles, but lack semantic metrics using word vectors for tweet form satirical news. Moreover, the vagueness of satire and news parody determines that a news tweet can hardly be classified with a binary decision, that is, satirical or legitimate. To address these issues, we collect satirical and legitimate news tweets, and propose a semantic feature based approach. Features are extracted by exploring inconsistencies in phrases, entities, and between main and relative clauses. We apply game-theoretic rough set model to detect satirical news, in which probabilistic thresholds are derived by game equilibrium and repetition learning mechanism. Experimental results on the collected dataset show the robustness and improvement of the proposed approach compared with Pawlak rough set model and SVM.