This paper presents a personalized recommendation system for TESOL learners based on Particle Swarm Optimization (PSO). The system aims to enhance the learning experience by offering tailored recommendations that optimize various metrics such as precision, recall, F1-score, diversity, novelty, relevance, accuracy, user satisfaction, and recommendation quality. The proposed PSO-based approach effectively improves the recommendation results by addressing the multi-objective optimization challenges inherent in personalized learning. Through a series of experiments, the PSO algorithm demonstrated superior performance over traditional collaborative filtering and content-based filtering methods, particularly in terms of diversity and novelty. The results highlight the potential of PSO in improving the relevance and effectiveness of recommendations in educational contexts, providing TESOL learners with more personalized, diverse, and valuable content. This research contributes to the development of advanced recommendation techniques that can be applied to other domains requiring personalized content delivery.