In today’s rapidly evolving digital landscape, customer reviews play a crucial role in shaping the reputation and success of hotels. Accurately analyzing and classifying the sentiment of these reviews offers valuable insights into customer satisfaction, enabling businesses to gain a competitive edge. This study undertakes a comparative analysis of traditional natural language processing (NLP) models, such as BERT and advanced large language models (LLMs), specifically GPT-4 omni and GPT-4o mini, both pre- and post-fine-tuning with few-shot learning. By leveraging an extensive dataset of hotel reviews, we evaluate the effectiveness of these models in predicting star ratings based on review content. The findings demonstrate that the GPT-4 omni family significantly outperforms the BERT model, achieving an accuracy of 67%, compared to BERT’s 60.6%. GPT-4o, in particular, excelled in accuracy and contextual understanding, showcasing the superiority of advanced LLMs over traditional NLP methods. This research underscores the potential of using sophisticated review evaluation systems in the hospitality industry and positions GPT-4o as a transformative tool for sentiment analysis. It marks a new era in automating and interpreting customer feedback with unprecedented precision.