A survey of visual analytics techniques for online education
Xiaoyan Kui, Naiming Liu, Qiang Liu, Jingwei Liu, Xiaoqian Zeng, Chao Zhang
Abstract
Visual analytics techniques are widely utilized to facilitate the exploration of online educational data. To help researchers better understand the necessity and the efficiency of these techniques in online education, we systematically review related works of the past decade to provide a comprehensive view of the use of visualization in online education problems. We establish a taxonomy based on the analysis goal and classify the existing visual analytics techniques into four categories: learning behavior analysis, learning content analysis, analysis of interactions among students, and prediction and recommendation. The use of visual analytics techniques is summarized in each category to show their benefits in different analysis tasks. At last, we discuss the future research opportunities and challenges in the utilization of visual analytics techniques for online education.