2018 年 20 巻 1 号 p. 31-44
More and more companies are putting emphasis on communication skill in the recruitment of their employees and adopt group discussion as part of recruitment interview. In our ongoing project, we aim to develop a training system that can provide advices to its users in improving the perception of their communication skill during group discussion. In order to realize this goal, a conceptual unit or a template of communication style is required. In this paper, we propose the use of functional roles of the participants in group discussion as this unit and report the investigation results on the issues related to adopting functional roles in the support system. At first, we define the functional roles which are considered to be appropriate for this purpose and show that the distribution of these roles indeed determines the impression of individual participant's communication skill. In order to incorporate the feature of functional roles into a real-time support system, the system needs to detect the participants' functional roles from low-level signals which can be processed by computers. In the second part of this paper, we propose a detection model with machine learning techniques and show this is possible. The dynamics of the spacial and temporal patterns of the participants' functional roles and their relationship with communication skill can be considered to provide hints for the strategy of the support system. In the third part of this paper, we assume that the current “conversational situation” can be represented by the combination of the functional roles of the participants and conducted the analysis on it. We first analyzed the relationship of the transitions of conversational situations and communication skill. We then analyzed the patterns of the next role of the current situation regarding to high communication skill participants and low ones. From the results, we found that the participants who were more active in the discussion are generally evaluated with high skill.
