Enhancing Intelligent Tutoring Systems through Octalysis Gamification and Adaptive AI Agents

Abstract

This research aims to address the challenges of student motivation and engagement in fundamental programming education by implementing the Octalysis Gamification Framework within an Intelligent Learning System. Traditional learning methods often fail to visualize abstract concepts or provide personalized feedback, leading to student demotivation. To overcome this, a platform named "Starcoder" was designed and built, integrating two conceptual pillars: the eight core drives of the Octalysis Framework and an AI-supported Intelligent Tutoring System (ITS). The system employs the Next.js framework and integrates the Gemini AI API (M.E.C.H.A.) to provide real-time, adaptive feedback and remedial learning paths. The effectiveness of the platform was evaluated using the Hedonic-Motivation System Adoption Model (HMSAM) with 54 respondents, comparing the gamified platform against traditional classroom methods. Evaluation results demonstrate that the platform significantly outperforms traditional methods, achieving an 86.44% score in Perceived Usefulness and an 85.56% score in Curiosity. Notably, Behavioral Intention to Use increased by 15.56% compared to the baseline. These findings demonstrate that the comprehensive integration of gamification frameworks with generative AI agents effectively enhances student motivation and immersion in technical education. Future work should focus on expanding the AI's capability to dynamically adjust gamification elements in real-time based on student performance.