Prediction of Group Learning Results from an Aggregation of Individual Understanding with Kit-Build Concept Map

With the development of information and communication technology, we can collect and analyze a variety of data for optimization. It is expected that the prediction of learning with the data enables a deep reflection for enhancing the learning experience. This paper describes a method to predict the group learning results from aggregation of an individual's understanding with the Kit-build concept map (KBmap). KBmap is a reconstruction-type concept map with automated diagnosis of the content. To test this method, we examined the prediction results from the data collected from a classroom lesson. The results show that most of the actual results are in good agreement with the prediction, and the comparison between the actual results and the predictions could be useful for the teacher.