혐오와 대항: 혐오표현 탐지 모델 평가를 위한 대항표현 데이터셋 구축
Countering the hatred: The counter-speech dataset in Korean for evaluating hate speech detection models
- 발행
- 2022 등록이 논문은 발행 시점을 확인하지 못해 원문 등록일을 적었습니다. KCI가 2005~2008년에 옛 논문을 몰아서 올린 탓에, 그 시기 등록분은 발행보다 평균 3~5년 늦습니다. 실제 발행연도는 더 이를 수 있습니다.
- 소속·발행
- 고려대학교
- 출처
- 국내 KCI
- 원문
- 원문 보기 ↗
개념
키워드
hate speech detection, counter-speech, language model, ethics in NLP, hate speech detection, counter-speech, language model, ethics in NLP
초록
This study argues for the necessity of a Korean counter-speech dataset for ethical and effective hate speech detection research. Counter-speech is a response to online hate in order to stop the spread of hate speech and is considered an alternative approach to deleting and blocking. However, since counter-speech often employs offensive language or linguistic structures similar to hate speech, even the state-of-the-art hate speech detection models usually classify it as hate speech. This false positive bias risks silencing the language of minorities and their allies. However, the evaluation of Korean hate speech detection models remains untouched due to the absence of a Korean counter-speech dataset. Thus, we introduce the first Korean counter-speech dataset with annotations about target groups. We then tested a Korean hate speech detection model with our dataset, revealing a significant drop in the model’s accuracy from 97.9% to 42.7%.