Enhancing Innovation Through Bayesian Networks in Recommender Learning Paths
Zakaria Tagdimi, Ikram Amzil, Youssef Jdidou, Souhaib Aammou · Advances in educational technologies and instructional design book series · 2023
In an era characterized by rapidly evolving educational paradigms, the imperative to foster innovation and facilitate personalized learning experiences cannot be overstated. Traditional recommendation algorithms, such as collaborative filtering and content-based approaches, have played a pivotal role in tailoring educational content to individual needs. However, these methods, though effective in many respects, tend to perpetuate established preferences, inadvertently stifling innovative thinking. This chapter explores the transformative potential of Bayesian networks within recommender systems to address these limitations. It begins by examining the restrictions inherent in conventional recommendation algorithms, emphasizing the significance of fostering innovation in education. Bayesian networks are introduced as a revolutionary solution capable of bridging these gaps. This chapter offers a comprehensive overview of how Bayesian networks can reshape the landscape of personalized learning.