DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship
Proceedings of the ACM on Human-Computer Interaction · 02.05.2025 · 9 (2) · 1-24
DOI: 10.1145/3710959 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 02.05.2025. Verfasst von Yaqiong Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Although there have been automated approaches and tools supporting toxicity censorship for social posts, most of them focus on detection. Toxicity censorship is a complex process, wherein detection is just an initial task and a user can have further needs such as rationale understanding and content modification. For this problem, we conduct a need-finding study to investigate people's diverse needs in toxicity censorship and then build a ChatGPT-based censorship tool named DeMod accordingly. DeMod is equipped with the features of explainable De tection and personalized Mod ification, providing fine-grained detection results, detailed explanations, and personalized modification suggestions. We also implemented the tool and recruited 35 Weibo users for evaluation. The results suggest DeMod's multiple strengths like the richness of functionality, the accuracy of censorship, and ease of use. Based on the findings, we further propose several insights into the design of content censorship systems.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, Y., Zhang, P., Gu, H., Lu, T., Qiao, S., Shu, Y., Shao, Y., & Gu, N. (2025). DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship. Proceedings of the ACM on Human-Computer Interaction, 9(2), 1-24. https://doi.org/10.1145/3710959
Vancouver
Li Y, Zhang P, Gu H, Lu T, Qiao S, Shu Y, et al. DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship. Proceedings of the ACM on Human-Computer Interaction. 2025;9(2):1-24. doi:10.1145/3710959
BibTeX
@article{Li2025,
author = {Li, Yaqiong and Zhang, Peng and Gu, Hansu and Lu, Tun and Qiao, Siyuan and Shu, Yubo and Shao, Yiyang and Gu, Ning},
title = {DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship},
journal = {Proceedings of the ACM on Human-Computer Interaction},
year = {2025},
volume = {9},
number = {2},
pages = {1--24},
doi = {10.1145/3710959}
}
EUVIMED