Evaluating the Data Analytic Features of Blackboard Learn 9.1

Learning Management Systems (LMSs) track and store vast quantities of data on student engagement with course content. Research shows that Higher Education Institutes can harness the power of this data to build a better understanding of student learning. This study is an exploratory Learning Analytics initiative to evaluate the inbuilt analytic features available within Blackboards LMS solution namely Blackboard Learn 9.1 to determine if it informs academic staff on student engagement. The two analytic features analysed in this study are Module Reports and Blackboard’s inbuilt early warning system called the “Retention Center”. Analysis of LMS variables extracted from these analytic features established a statistically significant weakly positive correlation between hit activity, login activity and student examination results. A statistically significant weakly positive correlation was also established between Multiple Choice Quiz (MQQ) score and examination results. These findings suggest that activity within LMS, measured by logins, hit activity and results in MCQs provide indicators of student academic performance. Lecturers involved in the study felt the analytic features provided them with a sense of student engagement with course modules and better understanding of their student cohorts.