arXiv:2012.09118
Exploring Thematic Coherence in Fake News
원문 초록
The spread of fake news remains a serious global issue; understanding and curtailing it is paramount. One way of differentiating between deceptive and truthful stories is by analyzing their coherence. This study explores the use of topic models to analyze the coherence of cross-domain news shared online. Experimental results on seven cross-domain datasets demonstrate that fake news shows a greater thematic deviation between its opening sentences and its remainder.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models
Constrained Non-negative Matrix Factorization for Guided Topic Modeling of Minority Topics
Evaluating Negative Sampling Approaches for Neural Topic Models
Seeded Poisson Factorization: Leveraging domain knowledge to fit topic models
Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models
Locating the Leading Edge of Cultural Change
토론
이 논문과 연결된 포럼 글이 아직 없습니다.