Dynamic Forecasting of Conversation Derailment

Yova Kementchedjhieva, Anders Søgaard


Abstract
Online conversations can sometimes take a turn for the worse, either due to systematic cultural differences, accidental misunderstandings, or mere malice. Automatically forecasting derailment in public online conversations provides an opportunity to take early action to moderate it. Previous work in this space is limited, and we extend it in several ways. We apply a pretrained language encoder to the task, which outperforms earlier approaches. We further experiment with shifting the training paradigm for the task from a static to a dynamic one to increase the forecast horizon. This approach shows mixed results: in a high-quality data setting, a longer average forecast horizon can be achieved at the cost of a small drop in F1; in a low-quality data setting, however, dynamic training propagates the noise and is highly detrimental to performance.
Anthology ID:
2021.emnlp-main.624
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7915–7919
Language:
URL:
https://aclanthology.org/2021.emnlp-main.624
DOI:
10.18653/v1/2021.emnlp-main.624
Bibkey:
Cite (ACL):
Yova Kementchedjhieva and Anders Søgaard. 2021. Dynamic Forecasting of Conversation Derailment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7915–7919, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Dynamic Forecasting of Conversation Derailment (Kementchedjhieva & Søgaard, EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.624.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.624.mp4