Development and Evaluation of a Learning Analytics Dashboard for Moodle Learning Management System

Learning analytics provides a potential for adapting learning, teaching and knowledge testing processes to individual needs. One of the ways of using learning analytics is a dashboard for providing feedback to students and teachers. This paper presents the development and evaluation of the learning analytics dashboard for students (LAD-S). The LAD-S displays three views: a look at student success, system activities and prediction based on machine learning algorithms. We have used LAD-S as a part of Moodle online courses, one during the second semester in the 2020/2021, and the other two during the first semester in the 2021/2022. A survey was designed to examine students' opinion about the LAD-S that included student's self-awareness, influence of the dashboard on learning effectiveness, satisfaction with the type of data collected, usefulness and ease-of-use, intention to use the learning analytics dashboard. Data from 33 undergraduate and graduate students were collected. The results have shown that students are satisfied with all examined aspects of the LAD-S above the average. Students express the greatest satisfaction for ease of use (M = 3.79), clarity of collected data (M = 3.6), usefulness (M = 3.6), SUS questionnaire ( M = 3.6), behavioral intention (M = 3.4) and satisfaction with individual functions of LAD-S (M= 3.4). Lower, yet above-average satisfaction was obtained for the impact of the LAD-S on more effective learning (M = 3.2); intention to use (M = 3.3) and satisfaction with the possibility of behavioral changes (M = 3.1). To verify the reliability of the measures used, the Cronbach's alpha reliability coefficient was calculated for each scale. Satisfactory reliability of all measures used was obtained, with alpha coefficients ranging from 0.704 for the SUS questionnaire to 0.942 for the ease-of-use measure.