"Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth

TL;DR

This paper explores how Chinese youth perceive toxic language differently from adults, creating a new dataset and improving toxicity detection methods by incorporating contextual features specific to youth perceptions.

Contribution

It introduces the first Chinese youth-toxicity dataset and demonstrates that adding contextual meta information enhances toxicity detection accuracy for youth-specific language.

Findings

Youth perception linked to contextual factors like source and text features

Incorporating meta information improves detection accuracy

Proposed insights for future youth-centered toxicity detection research

Abstract

Risk perception is subjective, and youth's understanding of toxic content differs from that of adults. Although previous research has conducted extensive studies on toxicity detection in social media, the investigation of youth's unique toxicity, i.e., languages perceived as nontoxic by adults but toxic as youth, is ignored. To address this gap, we aim to explore: 1) What are the features of ``youth-toxicity'' languages in social media (RQ1); 2) Can existing toxicity detection techniques accurately detect these languages (RQ2). For these questions, we took Chinese youth as the research target, constructed the first Chinese ``youth-toxicity'' dataset, and then conducted extensive analysis. Our results suggest that youth's perception of these is associated with several contextual factors, like the source of an utterance and text-related features. Incorporating these meta information into current toxicity detection methods significantly improves accuracy overall. Finally, we propose several insights into future research on youth-centered toxicity detection.