Details
| Original language | English |
|---|---|
| Title of host publication | ASONAM '23 |
| Subtitle of host publication | Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining |
| Editors | B. Aditya Prakash, Dong Wang, Tim Weninger |
| Pages | 121-125 |
| Number of pages | 5 |
| Publication status | Published - 15 Mar 2024 |
| Event | 15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023 - Kusadasi, Turkey Duration: 6 Nov 2023 → 9 Nov 2023 |
Abstract
Hate speech detection systems may exhibit discriminatory behaviours. Research in this field has focused primarily on issues of discrimination toward the language use of minoritised communities and non-White aligned English. The interrelated issues of bias, model robustness, and disproportionate harms are weakly addressed by recent evaluation approaches, which capture them only implicitly. In this paper, we recruit a multidisciplinary group of experts to bring closer this divide between fairness and trustworthy model evaluation. Specifically, we encourage the experts to discuss not only the technical, but the social, ethical, and legal aspects of this timely issue. The discussion sheds light on critical bias facets that require careful considerations when deploying hate speech detection systems in society. Crucially, they bring clarity to different approaches for assessing, becoming aware of bias from a broader perspective, and offer valuable recommendations for future research in this field.
Keywords
- bias, hate speech, multidisciplinary methods
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Information Systems
- Decision Sciences(all)
- Information Systems and Management
- Engineering(all)
- Safety, Risk, Reliability and Quality
- Psychology(all)
- Social Psychology
- Social Sciences(all)
- Communication
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
ASONAM '23: Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. ed. / B. Aditya Prakash; Dong Wang; Tim Weninger. 2024. p. 121-125.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A Multidisciplinary Lens of Bias in Hate Speech
AU - Reyero Lobo, Paula
AU - Kwarteng, Joseph
AU - Russo, Mayra
AU - Fahimi, Miriam
AU - Scott, Kristen
AU - Ferrara, Antonio
AU - Sen, Indira
AU - Fernandez, Miriam
N1 - Funding Information: This work has received funding from the European Union’s Horizon 2020 research and innovation programme under Marie Sklodowska-Curie Actions (grant agreement number 860630) for the project “NoBIAS
PY - 2024/3/15
Y1 - 2024/3/15
N2 - Hate speech detection systems may exhibit discriminatory behaviours. Research in this field has focused primarily on issues of discrimination toward the language use of minoritised communities and non-White aligned English. The interrelated issues of bias, model robustness, and disproportionate harms are weakly addressed by recent evaluation approaches, which capture them only implicitly. In this paper, we recruit a multidisciplinary group of experts to bring closer this divide between fairness and trustworthy model evaluation. Specifically, we encourage the experts to discuss not only the technical, but the social, ethical, and legal aspects of this timely issue. The discussion sheds light on critical bias facets that require careful considerations when deploying hate speech detection systems in society. Crucially, they bring clarity to different approaches for assessing, becoming aware of bias from a broader perspective, and offer valuable recommendations for future research in this field.
AB - Hate speech detection systems may exhibit discriminatory behaviours. Research in this field has focused primarily on issues of discrimination toward the language use of minoritised communities and non-White aligned English. The interrelated issues of bias, model robustness, and disproportionate harms are weakly addressed by recent evaluation approaches, which capture them only implicitly. In this paper, we recruit a multidisciplinary group of experts to bring closer this divide between fairness and trustworthy model evaluation. Specifically, we encourage the experts to discuss not only the technical, but the social, ethical, and legal aspects of this timely issue. The discussion sheds light on critical bias facets that require careful considerations when deploying hate speech detection systems in society. Crucially, they bring clarity to different approaches for assessing, becoming aware of bias from a broader perspective, and offer valuable recommendations for future research in this field.
KW - bias
KW - hate speech
KW - multidisciplinary methods
UR - http://www.scopus.com/inward/record.url?scp=85190626293&partnerID=8YFLogxK
U2 - 10.1145/3625007.3627491
DO - 10.1145/3625007.3627491
M3 - Conference contribution
AN - SCOPUS:85190626293
SN - 9798400704093
SP - 121
EP - 125
BT - ASONAM '23
A2 - Aditya Prakash, B.
A2 - Wang, Dong
A2 - Weninger, Tim
T2 - 15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023
Y2 - 6 November 2023 through 9 November 2023
ER -