TY  - INPR
AV  - public
EP  - 5
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions.
ID  - discovery10199285
A1  - Johnston, Laura J
A1  - Jendoubi, Takoua
PB  - IEEE
Y1  - 2024/07/08/
N2  - In the context of higher education's evolving dynamics post-COVID-19, this paper assesses the impact of new pedagogical incentives implemented in a first-year undergraduate computing module at University College London. We employ a mixed methods approach, combining learning analytics with qualitative data, to evaluate the effectiveness of these incentives on increasing student engagement. A longitudinal overview of resource interactions is mapped through Bayesian network analysis of Moodle activity logs from 204 students. This analysis identifies early resource engagement as a predictive indicator of continued engagement while also suggesting that the new incentives disproportionately benefit highly engaged students. Focus group discussions complement this analysis, providing insights into student perceptions of the pedagogical changes and the module design. These qualitative findings underscore the challenge of sustaining engagement through the new incentives and highlight the importance of communication in blended learning environments. Our paper introduces an interpretable and actionable model for student engagement, which integrates objective, data-driven analysis with students' perspectives. This model provides educators with a tool to evaluate and improve instructional strategies. By demonstrating the effectiveness of our mixed methods approach in capturing the intricacies of student behaviour in digital learning environments, we underscore the model's potential to improve online pedagogical practices across diverse educational settings.
TI  - Evaluating Pedagogical Incentives in Undergraduate Computing: A Mixed Methods Approach Using Learning Analytics
KW  - Computer Science
KW  -  computer science education
KW  -  Computer Science
KW  -  Interdisciplinary Applications
KW  -  curriculum development
KW  -  DYNAMIC BAYESIAN NETWORKS
KW  -  Education & Educational Research
KW  -  Education
KW  -  Scientific Disciplines
KW  -  educational technology
KW  -  Engineering
KW  -  Engineering
KW  -  Multidisciplinary
KW  -  learning management systems
KW  -  ONLINE
KW  -  Science & Technology
KW  -  Social Sciences
KW  -  statistical learning
KW  -  Technology
UR  - http://dx.doi.org/10.1109/educon60312.2024.10578692
ER  -