Abstract
People in business companies and academic fields work in cooperation with others rather than working alone. They may discuss their progress with others, like co-workers and supervisors, to help them obtain the best results. Sometimes people may feel that such discussions are not conducted well. However, people do not evaluate the quality of each discussion every time because it is tough work for them; they usually do not have enough time for that. In the process of evaluating discussions, people might look back on their discussions and make a plan to have an improved discussion next time. This paper proposes an evaluation method for one-to-one research discussions. The method makes a model of the discussion process with transitions of utterance types. The labels of utterance types are assigned to each utterance in a discussion text manually. By calculating the transition probabilities between two labels, a matrix of transition probabilities is obtained. The transitions of labels with high probabilities are extracted from high quality discussions and connected to obtain a discussion process model. The model can be used for the evaluation of new discussions. We applied the proposed method to discussion texts and found that the obtained process model from high quality discussions had several loops of transitions which were connected loosely.
Information
タイトル：Analysis Method for One-to-one Discussion Process for Research Progress using Transition Probability of Utterance Type
著者：Seiya Tsuji, Yoko Nishihara, Wataru Sunayama, Ryosuke Yamanishi and Shiho Imashiro
概要：People in business companies and academic fields work in cooperation with others rather than working alone. They may discuss their progress with others, like co-workers and supervisors, to help them obtain the best results. Sometimes people may feel that such discussions are not conducted well. However, people do not evaluate the quality of each discussion every time because it is tough work for them; they usually do not have enough time for that. In the process of evaluating discussions, people might look back on their discussions and make a plan to have an improved discussion next time. This paper proposes an evaluation method for one-to-one research discussions. The method makes a model of the discussion process with transitions of utterance types. The labels of utterance types are assigned to each utterance in a discussion text manually. By calculating the transition probabilities between two labels, a matrix of transition probabilities is obtained. The transitions of labels with high probabilities are extracted from high quality discussions and connected to obtain a discussion process model. The model can be used for the evaluation of new discussions. We applied the proposed method to discussion texts and found that the obtained process model from high quality discussions had several loops of transitions which were connected loosely.
書籍情報：The Thirteenth International Conference on Advances in Computer-Human Interactions, pp.157-160
発表種別：国際会議論文
発表日：2020年3月