摘要：Visual learning analytics (VLA) tools and technologies enable the meaningful exchangeof information between educational data and teachers. This allows teachers to create meaningfulgroups of students based on possible collaboration and productive discussions. VLA tools alsoallow a better understanding of students’ educational demands. Finding similar samples in hugeeducational datasets, however, involves the use of effective similarity measures that represent theteacher’s purpose. In this study, we conducted a user study and improved our web-based similaritybased grouping VLA tool, (SBGTool) to help teachers categorize students into groups based on theirsimilar learning outcomes and activities. SBGTool v2.0 differs from SBGTool due to design changesmade in response to teacher suggestions, the addition of sorting options to the dashboard table, theaddition of a dropdown component to group the students into classrooms, and improvement in somevisualizations. To counteract color blindness, we have also considered a number of color palettes. Byapplying SBGTool v2.0, teachers may compare the outcomes of individual students inside a classroom,determine which subjects are the most and least difficult over the period of a week or an academicyear, identify the numbers of correct and incorrect responses for the most difficult and easiest subjects,categorize students into various groups based on their learning outcomes, discover the week with themost interactions for examining students’ engagement, and find the relationship between students’activity and study success. We used 10,000 random samples from the EdNet dataset, a large-scalehierarchical educational dataset consisting of student–system interactions from multiple platformsat the university level, collected over a two-year period, to illustrate the tool’s efficacy. Finally, weprovide the outcomes of the user study that evaluated the tool’s effectiveness. The results revealedthat even with limited training, the participants were able to complete the required analysis tasks.Additionally, the participants’ feedback showed that the SBGTool v2.0 gained a good level of supportfor the given tasks, and it had the potential to assist teachers in enhancing collaborative learning intheir classrooms.
关键词：visual learning analytics;learning analytics dashboard;SBGTool;similarity-basedgrouping;data visualization;educational data;EdNet;user study
