Authors

Ashish Shrikant

Department of Artificial Intelligence & Data Science, Nutan Maharashtra Institute of Engineering and Technology (NMIET), Maharashtra, India

Abstract

The rapid growth of online hotel booking platforms has generated a vast amount of customer reviews that contain valuable insights into guest satisfaction, service quality, and overall hospitality experiences. However, manually analyzing these unstructured textual reviews is time-consuming, inconsistent, and incapable of processing large-scale data efficiently. This research proposes a hybrid machine learning and BERT-based approach for sentiment and emotion analysis of hotel reviews to automatically identify customer opinions and emotional expressions with high accuracy. The proposed framework integrates Natural Language Processing (NLP) techniques with traditional machine learning algorithms and transformer-based deep learning models to perform comprehensive review analysis. Initially, the collected hotel reviews undergo preprocessing steps including text normalization, tokenization, stop-word removal, punctuation cleaning, and lemmatization to improve text quality. Feature extraction is performed using TF-IDF and contextual word embeddings generated by Bidirectional Encoder Representations from Transformers (BERT). The sentiment classification module employs hybrid learning models comprising Support Vector Machine (SVM), Random Forest (RF), and BERT-based classifiers to categorize reviews into positive, negative, and neutral sentiments. Simultaneously, the emotion analysis module identifies emotional states such as happiness, satisfaction, sadness, anger, frustration, and surprise expressed by customers. Furthermore, aspect-based sentiment analysis is incorporated to evaluate customer opinions regarding hotel attributes including staff behavior, cleanliness, room quality, food services, pricing, and amenities. Experimental evaluation demonstrates that the hybrid BERT-based framework significantly improves classification accuracy, contextual understanding, and emotion recognition compared with conventional machine learning methods. The proposed system effectively transforms large volumes of unstructured customer feedback into meaningful business intelligence, enabling hotel managers to monitor service quality, detect customer dissatisfaction at an early stage, enhance guest experiences, and support data-driven decision-making for continuous service improvement.

Keywords

Natural Language Processing (NLP) Sentiment Analysis Emotion Analysis Hotel Reviews Machine Learning BERT Transformer Model Support Vector Machine (SVM) Random Forest Aspect-Based Sentiment Analysis Text Mining Deep Learning Opinion Mining Customer Experience Analytics Hospitality Analytics.

Citation of this Article

Ashish Shrikant. (2026). A Hybrid Machine Learning and BERT-Based Approach for Sentiment and Emotion Analysis of Hotel Reviews. International Current Journal of Engineering and Science (ICJES), 5(7), 8-16. Article DOI: https://doi.org/10.47001/ICJES/2026.507002 

Licence Copyright (c) 2026 International Current Journal of Engineering and Science. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment Classification Using Machine Learning Techniques. Proceedings of the ACL-2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), 79–86.
  2. Liu, B. (2012). Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers.
  3. Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment Analysis Algorithms and Applications: A Survey. Ain Shams Engineering Journal, 5(4), 1093–1113.
  4. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
  5. Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NeurIPS), 30, 5998–6008.
  6. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781.
  7. Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: Global Vectors for Word Representation. Proceedings of EMNLP 2014, 1532–1543.
  8. Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
  9. Cambria, E., Schuller, B., Xia, Y., & Havasi, C. (2013). New Avenues in Opinion Mining and Sentiment Analysis. IEEE Intelligent Systems, 28(2), 15–21.
  10. Zhang, L., Wang, S., & Liu, B. (2018). Deep Learning for Sentiment Analysis: A Survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), e1253.
  11. Sun, C., Huang, L., & Qiu, X. (2019). Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence. Proceedings of NAACL-HLT 2019, 380–385.
  12. Schouten, K., & Frasincar, F. (2016). Survey on Aspect-Level Sentiment Analysis. IEEE Transactions on Knowledge and Data Engineering, 28(3), 813–830.
  13. Ravi, K., & Ravi, V. (2015). A Survey on Opinion Mining and Sentiment Analysis: Tasks, Approaches and Applications. Knowledge-Based Systems, 89, 14–46.
  14. Hu, M., & Liu, B. (2004). Mining and Summarizing Customer Reviews. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 168–177.
  15. Khan, F. H., Bashir, S., & Qamar, U. (2014). TOM: Twitter Opinion Mining Framework Using Hybrid Classification Scheme. Decision Support Systems, 57, 245–257.
  16. B. Pang and L. Lee, “Opinion mining and sentiment analysis,” Foundations and Trends in Information Retrieval, vol. 2, no. 1–2, pp. 1–135, 2008.
  17. B. Liu, Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012.
  18. S. M. Mohammad and P. D. Turney, “Crowdsourcing a word–emotion association lexicon,” Computational Intelligence, vol. 29, no. 3, pp. 436–465, 2013.
  19. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019.
  20. E. Cambria, B. Schuller, Y. Xia, and C. Havasi, “New avenues in opinion mining and sentiment analysis,” IEEE Intelligent Systems, vol. 35, no. 2, pp. 15–21, 2020.
  21. V. Jain and S. Kulkarni, “Text classification using sentiment analysis,” International Journal of Computer Science and Information Technologies, vol. 5, no. 3, pp. 3850–3854, 2014.
  22. G. Miner et al., Practical Text Mining and Statistical Analysis for Business Intelligence. Academic Press, 2012.
  23. C. C. Aggarwal, Machine Learning for Text. Springer International Publishing, 2018.
  24. T. Chen et al., “XGBoost: A scalable tree boosting system,” in Proc. ACM SIGKDD, 2016.
  25. R. Feldman, “Techniques and applications for sentiment analysis,” Communications of the ACM, vol. 56, no. 4, pp. 82–89, 2013.
  26. P. Ekman, “An argument for basic emotions,” Cognition and Emotion, vol. 6, no. 3–4, pp. 169–200, 1992.
  27. R. Plutchik, “The nature of emotions,” American Scientist, vol. 89, no. 4, pp. 344–350, 2001.
  28. K. R. Scherer, “What are emotions? And how can they be measured?” Social Science Information, vol. 44, no. 4, pp. 695–729, 2005.
  29. S. M. Kim and E. Hovy, “Determining the sentiment of opinions,” in Proc. COLING, 2004.
  30. P. D. Turney, “Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews,” in Proc. ACL, 2002.