Adaptive Mobile-Assisted Programming Education: Design, Implementation, Evaluation

Thesis Abstract

In the wake of rising mobile device penetration and the demand for scalable programming education, traditional classroom-based approaches often fail to accommodate diverse learner paces, contexts, and prior knowledge, leading to gaps in attainment and low intrinsic motivation. This study addresses the problem by designing, implementing, and evaluating an adaptive mobile-assisted programming education (AMAPE) system that personalizes learning trajectories, feedback, and resource recommendations to individual students' proficiencies and contexts. The aim is to enhance conceptual understanding, procedural fluency, and retention in introductory programming through just-in-time, context-aware interventions delivered via smartphones and tablets. Specific objectives are (1) to develop an adaptive instructional architecture that integrates cognitive apprenticeship, zone of proximal development, and self-regulated learning principles; (2) to implement modular mobile learning paths for Python programming, incorporating dynamic difficulty adjustment, formative assessment, and contextual hints; (3) to evaluate the impact of AMAPE on learning outcomes, motivation, and self-regulated learning strategies; (4) to examine user experience, accessibility, and technical feasibility across diverse student populations; and (5) to provide design guidelines for scalable deployment in higher education settings. A mixed-methods research design is employed, combining a quasi-experimental trial and qualitative inquiry. The population consists of first-year computer science and information technology students enrolled at a mid-sized university. A sample of 320 students is recruited and randomly assigned to an experimental group (n=160), which uses the AMAPE system for a 12-week introductory Python module, and a control group (n=160), which follows the standard instructor-led curriculum with static digital resources. Data collection instruments include standardized pre- and post-tests assessing programming concepts and procedural fluency, a validated motivation scale, and a self-regulated learning questionnaire. System-generated metrics capture engagement (time-on-task, session frequency), accuracy of code submissions, hint usage, and dropout rates. For qualitative insights, purposive sampling selects 30 students for semi-structured interviews and 6 focus groups with 24 instructors and teaching assistants to explore pedagogical impact and implementation challenges. Validity and reliability are ensured through pilot testing of instruments, Cronbach’s alpha checks (? ? 0.78 for scales), and triangulation across quantitative and qualitative data. Data analysis comprises (i) ANCOVA to compare post-test gains between groups while controlling for baseline performance; (ii) multilevel modeling to examine differential effects across learner profiles and weeks; (iii) regression analyses to identify predictors of learning gains and sustained engagement; (iv) thematic analysis for interview and focus group transcripts to elucidate perceived value, usability, and barriers; and (v) a qualitative synthesis to triangulate quantitative findings with user experiences. The theoretical framework integrates constructivist learning theory, cognitive load theory, and the theory of planned behavior to interpret motivational and behavioral outcomes, with the adaptive engine operationalized through an algorithmic model that combines Bayesian knowledge tracing and reinforcement learning to tailor content and feedback. Key expected findings include (i) statistically significant improvements in post-test scores for the AMAPE group (p < .05) with larger gains among low-baseline performers, (ii) higher motivation and greater use of self-regulated learning strategies in the experimental condition, (iii) longer and more efficient study sessions correlated with improved procedural fluency, and (iv) positive qualitative evidence of enhanced perceived autonomy and perceived usefulness of context-specific hints, balanced by identified usability and accessibility constraints. The study contributes to knowledge by providing empirical evidence on the effectiveness of adaptive mobile-assisted programming education in higher education, detailing an end-to-end design and evaluation framework, and proposing an integrative instructional model that synergizes cognitive, motivational, and technological perspectives. Practical implications include actionable guidelines for implementing adaptive mobile programming curricula at scale, considerations for equitable access, and recommendations for aligning assessment with adaptive learning pathways. The main conclusion anticipates that AMAPE can significantly enhance learning outcomes and engagement in introductory programming when learners receive timely, personalized support within a mobile platform, and it recommends iterative refinement of the adaptive algorithms, extended deployment across diverse disciplines, and longitudinal studies to assess long-term retention and transfer of programming skills.