Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions. / Kaffee, Lucie-aimée; Arora, Arnav; Augenstein, Isabelle.

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2023. s. 5891-5909.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Kaffee, L, Arora, A & Augenstein, I 2023, Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions. i Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), s. 5891-5909, 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, 06/12/2023. https://doi.org/10.18653/v1/2023.emnlp-main.361

APA

Kaffee, L., Arora, A., & Augenstein, I. (2023). Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions. I Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (s. 5891-5909). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.emnlp-main.361

Vancouver

Kaffee L, Arora A, Augenstein I. Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions. I Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL). 2023. s. 5891-5909 https://doi.org/10.18653/v1/2023.emnlp-main.361

Author

Kaffee, Lucie-aimée ; Arora, Arnav ; Augenstein, Isabelle. / Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2023. s. 5891-5909

Bibtex

@inproceedings{376b7820888940cb80b046272aa98560,
title = "Why Should This Article Be Deleted?: Transparent Stance Detection in Multilingual Wikipedia Editor Discussions",
abstract = "The moderation of content on online platforms is usually non-transparent. On Wikipedia, however, this discussion is carried out publicly and editors are encouraged to use the content moderation policies as explanations for making moderation decisions. Currently, only a few comments explicitly mention those policies – 20% of the English ones, but as few as 2% of the German and Turkish comments. To aid in this process of understanding how content is moderated, we construct a novel multilingual dataset of Wikipedia editor discussions along with their reasoning in three languages. The dataset contains the stances of the editors (keep, delete, merge, comment), along with the stated reason, and a content moderation policy, for each edit decision. We demonstrate that stance and corresponding reason (policy) can be predicted jointly with a high degree of accuracy, adding transparency to the decision-making process. We release both our joint prediction models and the multilingual content moderation dataset for further research on automated transparent content moderation.",
author = "Lucie-aim{\'e}e Kaffee and Arnav Arora and Isabelle Augenstein",
year = "2023",
doi = "10.18653/v1/2023.emnlp-main.361",
language = "English",
pages = "5891--5909",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
publisher = "Association for Computational Linguistics (ACL)",
address = "United States",
note = "2023 Conference on Empirical Methods in Natural Language Processing ; Conference date: 06-12-2023 Through 10-12-2023",

}

RIS

TY - GEN

T1 - Why Should This Article Be Deleted?

T2 - 2023 Conference on Empirical Methods in Natural Language Processing

AU - Kaffee, Lucie-aimée

AU - Arora, Arnav

AU - Augenstein, Isabelle

PY - 2023

Y1 - 2023

N2 - The moderation of content on online platforms is usually non-transparent. On Wikipedia, however, this discussion is carried out publicly and editors are encouraged to use the content moderation policies as explanations for making moderation decisions. Currently, only a few comments explicitly mention those policies – 20% of the English ones, but as few as 2% of the German and Turkish comments. To aid in this process of understanding how content is moderated, we construct a novel multilingual dataset of Wikipedia editor discussions along with their reasoning in three languages. The dataset contains the stances of the editors (keep, delete, merge, comment), along with the stated reason, and a content moderation policy, for each edit decision. We demonstrate that stance and corresponding reason (policy) can be predicted jointly with a high degree of accuracy, adding transparency to the decision-making process. We release both our joint prediction models and the multilingual content moderation dataset for further research on automated transparent content moderation.

AB - The moderation of content on online platforms is usually non-transparent. On Wikipedia, however, this discussion is carried out publicly and editors are encouraged to use the content moderation policies as explanations for making moderation decisions. Currently, only a few comments explicitly mention those policies – 20% of the English ones, but as few as 2% of the German and Turkish comments. To aid in this process of understanding how content is moderated, we construct a novel multilingual dataset of Wikipedia editor discussions along with their reasoning in three languages. The dataset contains the stances of the editors (keep, delete, merge, comment), along with the stated reason, and a content moderation policy, for each edit decision. We demonstrate that stance and corresponding reason (policy) can be predicted jointly with a high degree of accuracy, adding transparency to the decision-making process. We release both our joint prediction models and the multilingual content moderation dataset for further research on automated transparent content moderation.

U2 - 10.18653/v1/2023.emnlp-main.361

DO - 10.18653/v1/2023.emnlp-main.361

M3 - Article in proceedings

SP - 5891

EP - 5909

BT - Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics (ACL)

Y2 - 6 December 2023 through 10 December 2023

ER -

ID: 381511874