Discussion Data Analytics

Abstract

Evidence-based research, such as research on big data applications, has been receiving much attention and has led to the proposal of techniques for improving the quality of life by storing and analyzing data on daily activities in large quantities. These types of techniques have been applied in the education sector, but a crucial problem remains to be overcome: it is generally difficult to record intellectual activities and accumulate and analyze such data on a large scale. Since this kind of data is not possible to compress in a manner, such as taking the average, it is necessary to maintain the original data as the instances of cases. Such human intellectual-activity data should be treated as big data in the near future. We have been developing a discussion mining system that records face-to-face meetings in detail, analyzes their content, and conducts knowledge discovery. Looking back on past discussion content by browsing documents, such as minutes, is an effective means for conducting future activities. In meetings at which some research topics are regularly discussed, such as seminars in laboratories, the presenters are required to discuss future issues by checking urgent matters from the discussion records. We call statements including advice or requests proposed at previous meetings “task statements” and propose a method for automatically extracting them. With this method, based on certain semantic attributes and linguistic characteristics of statements, a statistical machine learning model is created using logistic regression analysis. A statement is judged whether it is a task statement according to its probability. We also developed a method that maintains the extraction accuracy by using the discussion mining system and its extension on the basis of task statement extraction over a long period. Specifically, we constructed an initial discriminant model of task statements and then applied active learning to new meeting minutes to improve the extraction accuracy. Active learning also has the advantage of reducing labeling costs in supervised machine learning. We explain the improvement in extraction accuracy and reduction in labeling costs with our method and confirm its effectiveness through simulations we conducted.