An AI-powered personalised self-learning system at the University of Kisubi. A cross-sectional study.

Abstract

Background:

Traditional learning approaches in higher education often fail to address the diverse learning needs of students due to limited personalised support, delayed feedback, and increasing class sizes. This study aimed to develop an AI-powered personalised self-learning system to improve learning experiences, increase student engagement, and enhance academic performance at the University of Kisubi.

Methodology:

A qualitative case study research design was adopted. The study was conducted at the University of Kisubi using a sample of 24 respondents comprising students, lecturers, administrators, and support staff selected through random sampling. Data were collected using questionnaires and analysed thematically to establish the functional and non-functional requirements of the proposed system. The identified requirements guided the design, development, implementation, testing, and validation of the AI-powered personalised self-learning system.

Results:

The study established that the existing learning system lacked personalised instruction, real-time feedback, adaptive learning pathways, and flexibility to accommodate diverse learner needs. Functional requirements identified included secure user registration and authentication, personalised learning paths, real-time feedback, interactive quizzes, content management, and performance analytics, while non-functional requirements emphasised usability, scalability, security, and system performance. The developed system was successfully implemented using HTML, CSS, JavaScript, PHP, and MySQL and incorporated AI-based adaptive learning features. System testing and user validation confirmed that all core functionalities operated as intended, enabling personalised content delivery, immediate feedback, efficient course management, learner progress tracking, and an intuitive user interface. The findings demonstrated the system's potential to improve student engagement, support self-paced learning, and enhance academic performance.

Conclusion:

The AI-powered personalised self-learning system successfully addressed the limitations of the existing learning approach by providing adaptive, learner-centred educational support.

 Recommendations:

Educational institutions should adopt and integrate AI-powered personalised learning systems into their teaching and learning processes to promote individualised instruction and continuous assessment.