Design and evaluate an adaptive e-learning system for programming skills development

Thesis Abstract

The rapid proliferation of programming education in recent years has underscored the need for personalized learning pathways that accommodate diverse learner profiles and enhance skill acquisition. Conventional e-learning platforms often employ static instructional modules, which may overlook individual learners' prior knowledge, learning pace, and specific difficulties, potentially limiting effectiveness in developing programming competencies. This study addresses the pressing challenge of designing an adaptive e-learning system tailored specifically for programming skills development, with the objective of improving learner engagement, mastery, and retention through contextualized and personalized instructional experiences. The primary aim of this research is to develop, implement, and evaluate a dynamic adaptive e-learning platform that adjusts content delivery based on real-time learner interactions and performance data. To achieve this, the study delineates specific objectives (1) to conceptualize a pedagogical framework integrating adaptive learning theories with programming education, (2) to design and develop the adaptive e-learning system incorporating learner modeling, content sequencing, and feedback mechanisms, (3) to evaluate the system’s effectiveness in enhancing programming skills among undergraduate students, and (4) to analyze learners’ engagement and satisfaction levels with the adaptive features. The research adopts a mixed-methods approach, integrating quantitative experimental design with qualitative insights. The quantitative component employs a quasi-experimental design involving a sample of 200 undergraduate students majoring in computer science, randomly assigned to experimental and control groups. The experimental group interacts with the adaptive e-learning system, while the control group uses a conventional non-adaptive platform. Data collection instruments include standardized programming competency tests, system usage logs, and Likert-scale questionnaires measuring learner engagement, motivation, and satisfaction. The qualitative data derive from semi-structured interviews with 20 participants from the experimental group to explore user experiences and perceptions. Data analysis applies statistical techniques such as multiple regression analysis to assess the impact of the adaptive system on programming skills, and t-tests to compare pre- and post-test performances. Thematic analysis is utilized to interpret qualitative feedback, providing contextual understanding of user experiences. Expected key findings suggest that learners using the adaptive system will demonstrate statistically significant improvements in programming competencies compared to the control group, with increased engagement and motivation levels. The adaptive features are anticipated to positively influence learners’ confidence and reduce misconceptions, thereby fostering deeper understanding of programming concepts. The research also aims to identify specific adaptive strategies that most effectively enhance learner outcomes, such as personalized content sequencing and immediate feedback. This study makes a significant contribution to the field of computer education by integrating adaptive learning theories—specifically the Situated Learning Theory and Cognitive Load Theory—with programming pedagogy to create a scalable, evidence-based model for personalized e-learning. It advances knowledge in the design of instructional systems that dynamically respond to learner needs, thus closing gaps in the literature regarding empirical validation of adaptive mechanisms in programming instruction. Additionally, the research provides a practical framework for educators and developers seeking to implement adaptive features in digital learning environments. The main conclusion highlights that adaptive e-learning systems, when effectively designed and implemented, can significantly improve programming skill development and learner motivation. Based on the findings, it is recommended that educational institutions adopt adaptive platforms to complement traditional teaching methods, invest in training educators to utilize such systems effectively, and further explore the integration of emerging technologies such as artificial intelligence for enhanced personalization. Future research should investigate longitudinal impacts of adaptive e-learning on programming mastery and extend the scope to include diverse learner populations and programming languages, thereby broadening the applicability and impact of adaptive learning innovations in computer education.