Saved in:
Bibliographic Details
Main Authors: Phi, Khiem, Faramarzi, Noushin Salek, Wang, Chenlu, Banerjee, Ritwik
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.09934
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914954074914816
author Phi, Khiem
Faramarzi, Noushin Salek
Wang, Chenlu
Banerjee, Ritwik
author_facet Phi, Khiem
Faramarzi, Noushin Salek
Wang, Chenlu
Banerjee, Ritwik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09934
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse
Phi, Khiem
Faramarzi, Noushin Salek
Wang, Chenlu
Banerjee, Ritwik
Computation and Language
Artificial Intelligence
I.2.7
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.
title Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse
topic Computation and Language
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2402.09934