Reproduce “Leveraging Large Language Models in Tourism: A Comparative Study of the Latest GPT Omni Models and BERT NLP for Customer Review Classification and Sentiment Analysis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Konstantinos I. Roumeliotis, Nikolaos D. Tselikas, Dimitrios K. Nasiopoulos
The study tests whether language models can predict hotel reviews’ exact one-to-five-star ratings from text. Fine-tuned GPT-4o and BERT models are compared with prompted base models on a held-out set of 1,000 reviews balanced across five ratings. Fine-tuned GPT-4o reached 67% accuracy, versus 60.6% for BERT. This measures exact rating prediction, not customer responses or performance on the original, skewed ratings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.