Answers are grounded in this paper and cite their sources.
In this paper, we discuss a task to recognize a participant’s behavior in a multi-party conversation. We focus on a detection task of a participant that returns to a discussion that is already over; we call the participant “BDH (Beat a Dead Horse) participant.” The target corpus contains 17 conversations about a topic with three participants, and one of three participants is the BDH participant. To detect the BDH participant, we apply machine learning methods. We compare three machine learning methods; naive bayes, decision tree, and support vector machines. In addition, we introduce a selection model based on the task setting. The experimental result shows the effectiveness of SVMs with our selection model.
No takes yet. Share an insight, caveat, or question.
Shimada et al. (2022) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: