Research on AI based Personalized Recommendation System for Foreign Language Learning using k-Nearest Neighbours

The advancement of artificial intelligence (AI) has enabled the development of intelligent educational systems, revolutionizing traditional foreign language learning approaches. However, existing platforms often suffer from a lack of personalization, employing static content delivery methods that fail to accommodate individual learner needs, preferences, and progress. This leads to disengaged learners and inefficient language acquisition. Addressing this problem requires a dynamic solution capable of tailoring learning content based on learner interactions and behavioral patterns. This research proposes an AI-based personalized recommendation system using the k-Nearest Neighbors (k-NN) algorithm to enhance the foreign language learning experience. Learner profiles are built by analyzing features such as learning behavior, content interactions, assessment results, and time spent on lessons. The k-NN algorithm computes similarities between learner profiles and available content using cosine similarity, identifying and recommending the top-k most relevant language resources tailored to individual needs. Experimental results show a significant improvement in learner engagement, retention, and learning outcomes compared to conventional language learning platforms. Evaluation metrics, including precision and recall validate the system's effectiveness in delivering personalized and accurate recommendations. The discussion highlights the flexibility of k-NN in educational contexts, its scalability for large datasets, and its adaptability to evolving learner preferences. This research demonstrates the potential of AI-driven systems in fostering dynamic, engaging, and efficient foreign language learning environments.