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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Yaqiong, Zhang, Peng, Wang, Lin, Gu, Hansu, Qiao, Siyuan, Gu, Ning, Lu, Tun
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911090161483776
author Li, Yaqiong
Zhang, Peng
Wang, Lin
Gu, Hansu
Qiao, Siyuan
Gu, Ning
Lu, Tun
author_facet Li, Yaqiong
Zhang, Peng
Wang, Lin
Gu, Hansu
Qiao, Siyuan
Gu, Ning
Lu, Tun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle "Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth
Li, Yaqiong
Zhang, Peng
Wang, Lin
Gu, Hansu
Qiao, Siyuan
Gu, Ning
Lu, Tun
Computation and Language
Human-Computer Interaction
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.
title "Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2508.02094