TY - GEN
T1 - Learning analytics for measuring engagement and academic performance: a case study from an Irish university
T2 - 8th International Conference on Higher Education Advances, HEAd 2022
AU - Lang, Michael
N1 - Publisher Copyright:
© HEAd 2022. All Rights Reserved.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - This paper presents an analysis of various metrics of student engagement and academic performance, based on data extracted from a virtual learning environment (VLE) and other supporting technologies. The level of student activity on the VLE, as measured by hours and count of accesses to content areas, was found to be a strong indicator of engagement and impacted the level of performance. Participation in self-regulated optional learning activities was also found to be a strong indicator of engagement, which again impacted students' scores. As regards gender comparisons, males and females demonstrated different study approaches but there was no difference in performance. Senior (final year) students out-performed sophomore (second year) students, and students on programmes with higher entry bars fared better. Interestingly, students who adopted a steady approach with consistent levels of activity through the semester achieved higher scores than those who procrastinated. The paper concludes with some recommendations on where learning analytics technologies need to go to truly be useful for teachers and students in higher education.
AB - This paper presents an analysis of various metrics of student engagement and academic performance, based on data extracted from a virtual learning environment (VLE) and other supporting technologies. The level of student activity on the VLE, as measured by hours and count of accesses to content areas, was found to be a strong indicator of engagement and impacted the level of performance. Participation in self-regulated optional learning activities was also found to be a strong indicator of engagement, which again impacted students' scores. As regards gender comparisons, males and females demonstrated different study approaches but there was no difference in performance. Senior (final year) students out-performed sophomore (second year) students, and students on programmes with higher entry bars fared better. Interestingly, students who adopted a steady approach with consistent levels of activity through the semester achieved higher scores than those who procrastinated. The paper concludes with some recommendations on where learning analytics technologies need to go to truly be useful for teachers and students in higher education.
KW - Academic performance
KW - Engagement
KW - Gender differences
KW - Learning analytics
KW - Structural equational modelling.
KW - Student behaviour
KW - Virtual learning environments
UR - https://www.scopus.com/pages/publications/85136992114
M3 - Conference Publication
T3 - 2603-5871
SP - 183
EP - 189
BT - International Conference on Higher Education Advances
PB - Universidad Politecnica de Valencia.
Y2 - 14 June 2022 through 17 June 2022
ER -