Host: The Japanese Society for Artificial Intelligence
Name : The 36th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 36
Location : [in Japanese]
Date : June 14, 2022 - June 17, 2022
When building consensus through group discussion, research has been conducted to comprehensively evaluate the dialogue based on consensus results and deliverables. However, whether the dialogue that took place was satisfactory or whether the results achieved are acceptable are influenced by the values that participants hold with respect to dialogue. The purpose of this paper is to estimate individual participants’ subjective evaluations of the dialogue using transcriptions of their utterances in group dialogue. We propose a technology for evaluating and estimating individual subjective evaluations of the dialogue, based on positivity and impact of a dialogue participant. As a result, it was found that positivity in the beginning portion of a dialogue and the impact of participant remarks during the middle and end of the dialogue affected subjective evaluation of the dialogue, respectively. The results show that it is possible to estimate individual participants’ subjective evaluations of the dialogue by using positivity and the impact of remarks, taking into account the time elapsed since the dialogue started and the stage of consensus building.