2017/02/18 by Martin Potthast, Potthast, Martin, Johannes Kiesel +7 · 1 voice · 61 citations
Computer Science · Social Sciences · #Art #Artificial intelligence #Authorship Attribution and Profiling #Computer science #Fake news #Image (mathematics) #Internet privacy #Law #Literature #Mainstream #Media studies #Misinformation and Its Impacts #Political science #Politics #Similarity (geometry) #Sociology #Spam and Phishing Detection #Style (visual arts) #Writing style #cs.CL
paper · pdf · doi:10.48550/arxiv.1702.05638
published in arXiv (Cornell University) (Cornell University) · 10 pages, 3 figures, 6 tables, submitted to ACL 2017
arxiv created 2017/02/18 · openalex publication_date 2017/02/18 · arxiv updated 2017/02/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
This paper reports on a writing style analysis of hyperpartisan (i.e., extremely one-sided) news in connection to fake news. It presents a large corpus of 1,627 articles that were manually fact-checked by professional journalists from BuzzFeed. The articles originated from 9 well-known political publishers, 3 each from the mainstream, the hyperpartisan left-wing, and the hyperpartisan right-wing. In sum, the corpus contains 299 fake news, 97% of which originated from hyperpartisan publishers. We propose and demonstrate a new way of assessing style similarity between text categories via Unmasking---a meta-learning approach originally devised for authorship verification---, revealing that the style of left-wing and right-wing news have a lot more in common than any of the two have with the mainstream. Furthermore, we show that hyperpartisan news can be discriminated well by its style from the mainstream (F1=0.78), as can be satire from both (F1=0.81). Unsurprisingly, style-based fake news detection does not live up to scratch (F1=0.46). Nevertheless, the former results are important to implement pre-screening for fake news detectors.