A Comprehensive Review of Hotel Recommendation Systems Using Reviews and AI

Hotel recommendation systems have become a vital component of modern tourism platforms due to the exponential growth of online hotel reviews and user-generated content. These systems assist travelers in making informed booking decisions by analyzing customer preferences, sentiments, and contextual factors. Recent advances in artificial intelligence, machine learning, and deep learning have significantly improved recommendation accuracy, personalization, and scalability. This review paper presents a comprehensive analysis of state-of-the-art hotel recommendation approaches published between 2024 and 2025, with particular emphasis on sentiment analysis, hybrid recommender models, deep learning architecture, and explainable AI techniques. The study systematically examines methodological trends, advantages, and limitations across existing works, highlighting how textual reviews, metadata, and contextual information are integrated into recommendation pipelines. Furthermore, this review identifies key research findings and challenges related to data sparsity, ambiguity in natural language, fairness, explainability, and ethical considerations. By synthesizing recent research contributions, this paper aims to provide a structured understanding of current progress and future research directions in hotel recommendation systems, offering valuable insights for researchers and practitioners working in intelligent tourism and hospitality analytics.