A personalized learning path recommendation algorithm for English listening learning leverages data on users' proficiency levels, learning preferences, and past performance to suggest tailored learning paths. By incorporating natural language processing (NLP) techniques, the algorithm can analyze audio content, transcripts, and user interactions to assess comprehension and identify areas for improvement. It then recommends a sequence of listening exercises, podcasts, audiobooks, or other resources matched to the user's skill level and interests. This paper introduces the Ranked Path Recommendation (RPR) algorithm, designed to facilitate personalized English listening learning. Leveraging data analytics and machine learning techniques, the RPR algorithm aims to provide tailored recommendations of listening materials based on individual learners' preferences, proficiency levels, and learning objectives. Through a series of experiments and analyses, the effectiveness of the algorithm is evaluated, considering factors such as recommendation accuracy, learner satisfaction, and adaptability. Results demonstrate the algorithm's ability to curate diverse and relevant listening materials, enhancing learner engagement and comprehension. However, challenges such as algorithmic biases and the need for ongoing refinement are acknowledged. Ultimately, the RPR algorithm represents a promising approach to adaptive learning in language education, contributing to the advancement of personalized and effective language learning experiences. Results demonstrate that the RPR algorithm achieved recommendation accuracy ranging from 85% to 92% across ten different scenarios, with corresponding learner satisfaction ratings ranging from 6.9 to 8.8 on a scale of 1 to 10. Learner feedback indicates that recommended materials were perceived as relevant, engaging, and diverse, contributing to enhanced comprehension and motivation.