Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse
This addresses the under-explored challenge of distinguishing whataboutism from related phenomena like propaganda in NLP, with incremental but specific gains for online content moderation.
The paper tackled the problem of detecting whataboutism in online discourse by introducing new datasets from Twitter and YouTube and developing a novel method using attention weights for negative sample mining, achieving improvements of 4% and 10% over previous state-of-the-art methods.
Whataboutism, a potent tool for disrupting narratives and sowing distrust, remains under-explored in quantitative NLP research. Moreover, past work has not distinguished its use as a strategy for misinformation and propaganda from its use as a tool for pragmatic and semantic framing. We introduce new datasets from Twitter and YouTube, revealing overlaps as well as distinctions between whataboutism, propaganda, and the tu quoque fallacy. Furthermore, drawing on recent work in linguistic semantics, we differentiate the `what about' lexical construct from whataboutism. Our experiments bring to light unique challenges in its accurate detection, prompting the introduction of a novel method using attention weights for negative sample mining. We report significant improvements of 4% and 10% over previous state-of-the-art methods in our Twitter and YouTube collections, respectively.