Design and evaluation of an AI-assisted personalized learning platform for computer education in secondary schools

Project Abstract

This study presents the design and evaluation of an AI-assisted personalized learning platform tailored for computer education in secondary schools, aiming to address diverse learner needs, enhance engagement, and improve learning outcomes. The platform integrates adaptive content delivery, intelligent tutoring, real-time feedback, and analytics to support teachers and students within standard curricula. A mixed-methods methodology was employed, combining a quasi-experimental design with a control group and an extensive teacher and student survey to assess usability, engagement, and perceived learning gains over a full academic term. The core pedagogical framework blends constructivist theories with mastery learning principles, leveraging AI to scaffold activities, adjust difficulty, and sequence prerequisite concepts in programming, computer architecture, databases, and digital literacy. The adaptive engine analyzes each learner’s prior knowledge, misconceptions, pace, and learning preferences to personalize task difficulty, hints, and remediation paths, while preserving core competencies and assessment alignment with national benchmarks. A modular content repository was developed, enabling rapid authoring and updating of lessons, simulations, and coding exercises across multiple programming languages and development environments. The platform features an AI-powered tutoring assistant that provides step-by-step guidance, exemplars, and diagnostic feedback on programming tasks, algorithm design, and debugging strategies. Automated formative assessments track progress, generate instant feedback, and adapt subsequent tasks to target identified gaps. Teacher dashboards offer actionable insights through dashboards and visualizations, enabling timely interventions, differentiation, and data-driven instruction. Privacy, data security, and ethical considerations were integral to the system design, with anonymized analytics, opt-in data collection, and transparent AI explainability for both students and educators. Quantitative outcomes indicate statistically significant improvements in high-stakes assessments and course completion rates for students using the platform compared with peers in the control group. The platform also demonstrated higher time-on-task, reduced error rates in introductory programming tasks, and improved self-efficacy regarding computing concepts. Qualitative findings from interviews and focus groups highlighted perceived benefits such as personalized pacing, clearer feedback, increased motivation, and greater autonomy in learning, while challenges included initial setup effort, variability in teacher adoption, and the need for ongoing professional development to maximize platform effectiveness. The study also examined equity considerations, revealing that the adaptive features helped bridge achievement gaps for students with diverse linguistic and cultural backgrounds, provided appropriate scaffolding for beginners, and offered advanced challenges for rapid learners, thereby supporting inclusive education. Limitations include a single-site implementation, a limited number of instructors, and a relatively short intervention window, which may affect generalizability. Recommendations for scalability encompass expanding domain coverage, integrating with school information systems, refining natural language interfaces, and providing sustained teacher training and peer collaboration opportunities. The research contributes to the evidence base on AI-enhanced personalized learning in secondary computer education by detailing the design rationale, pedagogical alignment, evaluation methods, and practical implications for policy, practice, and future research.

Project Overview

What This Project Is About

---

A straightforward study of creating and testing an adaptive learning platform that uses artificial intelligence to tailor computer education content to individual secondary school students. It explores how technology can adjust lessons, practice problems, and feedback based on how each student learns.

---

---

The Problem It Addresses

---

---

---

Objectives of the Project

---

1. Understand basic concepts of AI as they apply to education.
2. Design a simple AI-driven personalization framework for computer lessons.
3. Implement a prototype platform with adjustable difficulty and feedback.
4. Test how the platform affects student learning in a controlled setting.
5. Evaluate usability and teacher acceptance of the tool.

---

---

What You Will Do Step by Step

---

1) Review existing teaching methods and learning platforms. 2) Collect baseline data from students (pre-tests, surveys). 3) Build a basic AI model that adjusts content based on responses. 4) Develop a user interface for students and a dashboard for teachers. 5) Run a small user trial and gather feedback. 6) Analyze results to see if learning improves and where it can be improved. 7) Document findings and practical recommendations.

---

---

---

---

Expected Outcome