Exploring Computer Science student engagement factors within the learning analytics context to increase their academic achievement

Abstract

The study aims to improve student retention rate and maintain student engagement level by exploring the student motivation factors within a learning analytics context. This research is an exploratory case study within the Computer Science Department at the University of Huddersfield, UK. The research focuses to develop a model to explore undergraduate CS student motivation factors through Self-Determination Theory and train the identified factors using learning analytics records. The identified factors will contribute to enhance the student academic achievement and their engagement with the course. In addition, the factors can be used to assist the future designer of learning analytics (LA) tools to adapt the human center design approach. Therefore, the new LA tools can incorporate cognitive and noncognitive factors that can enhance student retention rate and engagement toward computer science department. The study adapts a mixed-method approach using survey, interview and learning analytics records. More than 10,000 thousand virtual learning environment records were analyzed from the year 2018 to 2021. The analysis findings revealed that there are 8 significant factors that can have an impact on CS student engagement and therefore affecting their final grade.