Title: Sentiment analysis of hotel reviews: an application of deep-learning based model

Authors: R. Murugesan; A.P. Rekha; Eva Mishra

Addresses: Department of Humanities and Social Sciences, National Institute of Technology, Tiruchirappalli, Tamil Nadu, 620015, India ' Department of Humanities and Social Sciences, National Institute of Technology, Tiruchirappalli, Tamil Nadu, 620015, India ' Chitkara University, Chandigarh-Patiala National Highway, NH- 64 Village Jansla, Rajpura, Punjab 140401, India

Abstract: Research demonstrates that researchers both from academia and industry are investigating profoundly for successful implementation of sentiment analysis from the uncountable number of hotel reviews being posted per second. Literature finds some constraints in the most frequently used machine learning techniques, BoW, N-grams, and highly effective word embedding methods, Word2vec and Glove warranting an effective model to fill the gap. As suggested by the research, our study applied the BERT-based CRRNN model for sentiment analysis of online hotel reviews which first of its kind for hotel reviews. Our model has exhibited good performance in comparison to most popular machine learning and word embeddings techniques. The evaluation metrics, prediction accuracy, recall, precision, and F-score including graphical representation for ROC and confusion matrix were evaluated to ensure the efficiency of the proposed model. Our sentiment analysis on hotel reviews using BERT-CBRNN will be immensely helpful for all the stakeholders.

Keywords: sentiment analysis; SA; hotel reviews; deep-learning-based model; word embeddings; BERT-CBRNN.

DOI: 10.1504/IJENM.2025.151282

International Journal of Enterprise Network Management, 2025 Vol.16 No.4, pp.309 - 338

Received: 16 Sep 2023
Accepted: 17 Mar 2024
Published online: 22 Jan 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article