Visual Analysis for Monitoring Students in Distance Courses

Abstract

With technological advances, distance education has been frequently discussed in recent years. The learning environments used in this course usually generates a great deal of data because of the large number of students and the various tasks involving their interaction. In order to facilitate the analysis of the data, the authors researched to identify how interaction and visualization techniques integrated with data mining algorithms can assist teachers in predicting students' performance in learning environments. The main goal of this work is to present the results of such research and the visual analysis approach that the authors developed in this context. This approach allows data gathering on the students' interactions and provides tools to investigate and predict pass/fail rates in the courses that are being analyzed. Our main contributions are: the visualization of the resources and their use by students; the possibility of making an individual analysis of students through interactive visualizations; and the ability to compare subjects in terms of students' performance.