Search papers, labs, and topics across Lattice.
This paper addresses the challenge of predicting conversational derailment in online discussions, particularly in low-data and cross-domain scenarios. By incorporating speech act information as an auxiliary learning signal, the authors enhance the model's ability to generalize beyond lexical variations. Experimental results demonstrate significant performance improvements across three datasets, highlighting the effectiveness of pragmatic representations in fostering proactive moderation.
Leveraging speech act information can dramatically enhance derailment forecasting accuracy, especially in low-data environments.
Conversational derailment forecasting aims to predict when online discussions will escalate into hostility, enabling proactive moderation. Existing approaches often struggle in low-data settings and to generalize across domains. This poses a challenge for new platforms and smaller communities where annotated data is limited. We propose modeling pragmatic representations of conversations to reduce lexical noise and improve generalizability. Specifically, speech act information is used as an auxiliary learning signal alongside textual semantics. Experimental results show improved performance across three datasets, particularly in low-data and cross-domain settings.
