Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse

• URL: http://arxiv.org/abs/2508.11434v1
• Date: Fri, 15 Aug 2025 12:24:22 GMT
• Title: Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse
• Authors: Aditi Dutta, Susan Banducci,
• Abstract summary: This study examines how five large language models classify sexist, anti-sexist, and neutral political tweets from the UK.<n>Our analysis show that models frequently misclassify anti-sexist speech as harmful, particularly during politically charged events.<n>We argue that moderation design must move beyond binary harmful/not-harmful schemas, integrate human-in-the-loop review during sensitive events, and explicitly include counter-speech in training data.
• Score: 0.7209758868768354
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Anti-sexist speech, i.e., public expressions that challenge or resist gendered abuse and sexism, plays a vital role in shaping democratic debate online. Yet automated content moderation systems, increasingly powered by large language models (LLMs), may struggle to distinguish such resistance from the sexism it opposes. This study examines how five LLMs classify sexist, anti-sexist, and neutral political tweets from the UK, focusing on high-salience trigger events involving female Members of Parliament in the year 2022. Our analysis show that models frequently misclassify anti-sexist speech as harmful, particularly during politically charged events where rhetorical styles of harm and resistance converge. These errors risk silencing those who challenge sexism, with disproportionate consequences for marginalised voices. We argue that moderation design must move beyond binary harmful/not-harmful schemas, integrate human-in-the-loop review during sensitive events, and explicitly include counter-speech in training data. By linking feminist scholarship, event-based analysis, and model evaluation, this work highlights the sociotechnical challenges of safeguarding resistance speech in digital political spaces.

Related papers

• Latent Topic Synthesis: Leveraging LLMs for Electoral Ad Analysis [51.95395936342771]
  We introduce an end-to-end framework for automatically generating an interpretable topic taxonomy from an unlabeled corpus.<n>We apply this framework to a large corpus of Meta political ads from the month ahead of the 2024 U.S. Presidential election.<n>Our approach uncovers latent discourse structures, synthesizes semantically rich topic labels, and annotates topics with moral framing dimensions.
  arXiv  Detail & Related papers  (2025-10-16T20:30:20Z)
• HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation [67.69631485036665]
  We conduct a comprehensive examination of hate speech regulations and strategies from three perspectives.<n>Our findings reveal significant inconsistencies in hate speech definitions and moderation practices across jurisdictions.<n>We suggest ideas and research direction for further exploration of a unified framework for automated hate speech moderation.
  arXiv  Detail & Related papers  (2025-07-06T11:25:23Z)
• MuSeD: A Multimodal Spanish Dataset for Sexism Detection in Social Media Videos [12.555579923843641]
  We introduce a new Multimodal Spanish dataset for Sexism Detection consisting of $approx$ 11 hours of videos extracted from TikTok and BitChute.<n>We find that visual information plays a key role in labeling sexist content for both humans and models.
  arXiv  Detail & Related papers  (2025-04-15T13:16:46Z)
• Gender Bias and Property Taxes [50.18156030818883]
  We analyze records of more than 100,000 property tax appeal hearings and more than 2.7 years of associated audio recordings.<n>Female appellants fare systematically worse than male appellants in their hearings.<n>Our results are consistent with the idea that gender biases are driven, at least in part, by unvoiced beliefs and perceptions on the part of ARB panelists.
  arXiv  Detail & Related papers  (2024-12-17T07:14:23Z)
• Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management [71.99446449877038]
  We propose a more comprehensive approach called Demarcation scoring abusive speech based on four aspect -- (i) severity scale; (ii) presence of a target; (iii) context scale; (iv) legal scale. Our work aims to inform future strategies for effectively addressing abusive speech online.
  arXiv  Detail & Related papers  (2024-06-27T21:45:33Z)
• A multitask learning framework for leveraging subjectivity of annotators to identify misogyny [47.175010006458436]
  We propose a multitask learning approach to enhance the performance of the misogyny identification systems. We incorporated diverse perspectives from annotators in our model design, considering gender and age across six profile groups. This research advances content moderation and highlights the importance of embracing diverse perspectives to build effective online moderation systems.
  arXiv  Detail & Related papers  (2024-06-22T15:06:08Z)
• Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias [8.168722337906148]
  This study investigates the presence of bias in harmful speech classification of gender-queer dialect online. We introduce a novel dataset, QueerLex, based on 109 curated templates exemplifying non-derogatory uses of LGBTQ+ slurs. We systematically evaluate the performance of five off-the-shelf language models in assessing the harm of these texts.
  arXiv  Detail & Related papers  (2024-05-23T18:07:28Z)
• A Multilingual Perspective on Probing Gender Bias [0.0]
  Gender bias is a form of systematic negative treatment that targets individuals based on their gender. This thesis investigates the nuances of how gender bias is expressed through language and within language technologies.
  arXiv  Detail & Related papers  (2024-03-15T21:35:21Z)
• Whose Side Are You On? Investigating the Political Stance of Large Language Models [56.883423489203786]
  We investigate the political orientation of Large Language Models (LLMs) across a spectrum of eight polarizing topics. Our investigation delves into the political alignment of LLMs across a spectrum of eight polarizing topics, spanning from abortion to LGBTQ issues. The findings suggest that users should be mindful when crafting queries, and exercise caution in selecting neutral prompt language.
  arXiv  Detail & Related papers  (2024-03-15T04:02:24Z)
• #ContextMatters: Advantages and Limitations of Using Machine Learning to Support Women in Politics [0.15749416770494704]
  ParityBOT was deployed across elections in Canada, the United States and New Zealand. It was used to analyse and classify more than 12 million tweets directed at women candidates and counter toxic tweets with supportive ones. We examine the rate of false negatives, where ParityBOT failed to pick up on insults directed at specific high profile women.
  arXiv  Detail & Related papers  (2021-09-30T22:55:49Z)
• Automatic Detection of Sexist Statements Commonly Used at the Workplace [0.9790236766474201]
  We present a dataset of sexist statements that are more likely to be said in the workplace. We also present a deep learning model that can achieve state-of-the art results.
  arXiv  Detail & Related papers  (2020-07-08T15:14:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.