Researchers have developed and evaluated strategies for generating contextualized AI-powered counterspeech to combat online toxicity. Unlike generic approaches, these new methods adapt to the conversational context and user history to enhance persuasiveness. A crowdsourcing experiment indicated that lightweight strategies integrating conversational context and user history improved perceived adequacy and persuasiveness, though personalization was not uniformly effective. The findings offer guidance for creating more personalized and responsible counterspeech systems to advance human-AI collaboration in online content moderation. AI
IMPACT Improves AI's ability to combat online toxicity through personalized and context-aware responses.
RANK_REASON The cluster contains a research paper detailing novel methods for AI-generated counterspeech. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- BERTScore
- BLEU
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- human–computer interaction
- ROUGE
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
