Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics |
| Subtitle of host publication | Human Language Technologies |
| Place of Publication | Albuquerque, New Mexico |
| Pages | 11360-11395 |
| ISBN (electronic) | 979-8-89176-189-6 |
| Publication status | Published - Apr 2025 |
Abstract
Keywords
- Computational Argumentation, Moderation, Positive Moderation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. Albuquerque, New Mexico, 2025. p. 11360-11395.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - It Is Not Only the Negative that Deserves Attention!
T2 - Understanding, Generation & Evaluation of (Positive) Moderation
AU - Jundi, Iman
AU - Vecchi, Eva Maria
AU - Quensel, Carlotta Nele Farina
AU - Falk, Neele
AU - Lapesa, Gabriella
PY - 2025/4
Y1 - 2025/4
N2 - Moderation is essential for maintaining and improving the quality of online discussions. This involves: (1) countering negativity, e.g. hate speech and toxicity, and (2) promoting positive discourse, e.g. broadening the discussion to involve other users and perspectives. While significant efforts have focused on addressing negativity, driven by an urgency to address such issues, this left moderation promoting positive discourse (henceforth PositiveModeration) under-studied. With the recent advancements in LLMs, Positive Moderation can potentially be scaled to vast conversations, fostering more thoughtful discussions and bridging the increasing divide in online interactions.We advance the understanding of Positive Moderation by annotating a dataset on 13 moderation properties, e.g. neutrality, clarity and curiosity. We extract instructions from professional moderation guidelines and use them to prompt LLaMA to generate such moderation. This is followed by extensive evaluation showing that (1) annotators rate generated higher than professional moderation, but still slightly prefer professional moderation in pairwise comparison, and (2) LLMs can be used to estimate human evaluation as an efficient alternative.
AB - Moderation is essential for maintaining and improving the quality of online discussions. This involves: (1) countering negativity, e.g. hate speech and toxicity, and (2) promoting positive discourse, e.g. broadening the discussion to involve other users and perspectives. While significant efforts have focused on addressing negativity, driven by an urgency to address such issues, this left moderation promoting positive discourse (henceforth PositiveModeration) under-studied. With the recent advancements in LLMs, Positive Moderation can potentially be scaled to vast conversations, fostering more thoughtful discussions and bridging the increasing divide in online interactions.We advance the understanding of Positive Moderation by annotating a dataset on 13 moderation properties, e.g. neutrality, clarity and curiosity. We extract instructions from professional moderation guidelines and use them to prompt LLaMA to generate such moderation. This is followed by extensive evaluation showing that (1) annotators rate generated higher than professional moderation, but still slightly prefer professional moderation in pairwise comparison, and (2) LLMs can be used to estimate human evaluation as an efficient alternative.
KW - Computational Argumentation
KW - Moderation
KW - Positive Moderation
U2 - 10.18653/v1/2025.naacl-long.567
DO - 10.18653/v1/2025.naacl-long.567
M3 - Conference contribution
SP - 11360
EP - 11395
BT - Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics
CY - Albuquerque, New Mexico
ER -