Re-examining Sexism and Misogyny Classification with Annotator Attitudes

TL;DR

This paper investigates how annotator attitudes influence sexism and misogyny labeling in datasets and explores how incorporating attitudinal data affects automated classification performance, revealing biases and challenges in current models.

Contribution

It introduces a methodology to analyze annotator attitudes in GBV datasets and demonstrates how attitudinal information can improve or complicate automated classification tasks.

Findings

Higher Right Wing Authoritarianism correlates with increased sexist labeling.

Including attitudinal info can improve classifier performance with structured prompts.

Models struggle with complex, imbalanced label sets reflecting annotator biases.

Abstract

Gender-Based Violence (GBV) is an increasing problem online, but existing datasets fail to capture the plurality of possible annotator perspectives or ensure the representation of affected groups. We revisit two important stages in the moderation pipeline for GBV: (1) manual data labelling; and (2) automated classification. For (1), we examine two datasets to investigate the relationship between annotator identities and attitudes and the responses they give to two GBV labelling tasks. To this end, we collect demographic and attitudinal information from crowd-sourced annotators using three validated surveys from Social Psychology. We find that higher Right Wing Authoritarianism scores are associated with a higher propensity to label text as sexist, while for Social Dominance Orientation and Neosexist Attitudes, higher scores are associated with a negative tendency to do so. For (2), we conduct classification experiments using Large Language Models and five prompting strategies, including infusing prompts with annotator information. We find: (i) annotator attitudes affect the ability of classifiers to predict their labels; (ii) including attitudinal information can boost performance when we use well-structured brief annotator descriptions; and (iii) models struggle to reflect the increased complexity and imbalanced classes of the new label sets.