Revisiting recommender systems: an investigative survey

This paper provides a thorough review of recommendation methods from academic literature, offering a taxonomy that classifies recommender systems (RSs) into categories like collaborative filtering, content-based systems, and hybrid systems. It examines effectiveness and challenges such as filter bubbles, the cold start issue, and reliance on traditional collaborative and content-based approaches. The survey traces the development of RSs, emphasizing machine learning and deep learning models in overcoming these challenges to deliver more accurate, personalized, and context-aware recommendations. Ethical considerations—including fairness, transparency, and trust—are highlighted as increasingly significant. The literature review discusses collaborative filtering, personalized recommender systems, and robustness strategies, identifies limitations in existing approaches, and suggests promising directions to enhance accuracy, diversity, and ethical practices.