Selecting ML/DL Algorithms for Gamification of Formative Assessment
Arif Husen, Neelam Alam, Muhammad Hasanain Chaudary, Shabib Aftab, Syed Shah Muhammad · Advances in computational intelligence and robotics book series · 2025
Gamification in formative assessment is a promising approach to enhance student engagement and learning in AI-era education. Machine learning enables personalized experiences and adaptive feedback, with advancements like Context-Aware ML, explainable ML, and self-attention models playing key roles. Determining the best approach for gamification requires careful analysis, as factors like algorithm transparency, adaptability, and educational complexity remain challenges. While reinforcement learning and collaborative filtering have been explored, their application in gamification lacks integration with recent ML developments. Hybrid models that combine multiple algorithms, empirical studies to evaluate effectiveness, and iterative refinement using user data offer potential solutions. This chapter will address these challenges and propose a framework (GOFA) for selecting optimal ML algorithms to enhance gamification strategies in formative assessments.