Sentiment Analysis of Hotel Reviews: Identifying Key Factors for Customer Satisfaction

Sameeksha  Dwivedi; Pankaj  Richhariya

doi:10.69968/ijisem.2025v4i2416-423

Authors

Sameeksha Dwivedi Research Scholar, Department of Computer Science, Bhopal Institute of Technology & Science.
Pankaj Richhariya HOD, Department of Computer Science, Bhopal Institute of Technology & Science.

DOI:

https://doi.org/10.69968/ijisem.2025v4i2416-423

Keywords:

sentiment analysis, machine learning, deep learning, LSTM

Abstract

Deep learning is a subfield of machine learning which has achieved great success in certain sentiment analysis and other natural language processing applications. Specifically, state-of-the-art outcomes in sentiment analysis tasks have been shown when deep neural networks are used. This study aimed to perform sentiment analysis on hotel reviews to improve the services based on customer feedback. After completing data cleansing and feature engineering, the study employed dataset of the 36,000 reviews of a variety of hotels and locales. Reviews with ratings below 2.0 were classified as negative, while those with ratings over 4.5 were classified as positive, thereby creating the desired variable. Random forest, Logistic regression, support vector machine, and Naive Bayes were among the machine learning techniques tested in this study. When compared to these other methods, nevertheless, suggested bidirectional LSTM model fared better, with an accuracy of 97.44%. Using the confusion matrix, ROC curve, and accuracy measures, the study assessed the model. The findings demonstrated that proposed model outperformed the baseline paper model by a wide margin, with an improvement in accuracy from 92% to 97.44% when using Bi-LSTM.

References

[1] Erevelles, Sunil, Nobuyuki Fukawa, and Linda Swayne. "Big Data consumer analytics and the transformation of marketing." Journal of business research 69.2 (2016): 897-904.https://doi.org/10.1016/j.jbusres.2015.07.001

[2] Yu, Liang-Chih, et al. "Using a contextual entropy model to expand emotion words and their intensity for the sentiment classification of stock market news." Knowledge-Based Systems 41 (2013): 89-97.https://doi.org/10.1016/j.knosys.2013.01.001

[3] Hagenau, Michael, Michael Liebmann, and Dirk Neumann. "Automated news reading: Stock price prediction based on financial news using context-capturing features." Decision Support Systems 55.3 (2013): 685-697.https://doi.org/10.1016/j.dss.2013.02.006

[4] Xu, Tao, Qinke Peng, and Yinzhao Cheng. "Identifying the semantic orientation of terms using S-HAL for sentiment analysis." Knowledge-Based Systems 35 (2012): 279-289.https://doi.org/10.1016/j.knosys.2012.04.011

[5] Maks, Isa, and Piek Vossen. "A lexicon model for deep sentiment analysis and opinion mining applications." Decision Support Systems 53.4 (2012): 680-688.https://doi.org/10.1016/j.dss.2012.05.025

[6] Qiu, Guang, et al. "DASA: dissatisfaction-oriented advertising based on sentiment analysis." Expert Systems with Applications 37.9 (2010): 6182-6191.https://doi.org/10.1016/j.eswa.2010.02.109

[7] Hatzivassiloglou, Vasileios, and Kathleen McKeown. "Predicting the semantic orientation of adjectives." 35th annual meeting of the association for computational linguistics and 8th conference of the european chapter of the association for computational linguistics. 1997.https://doi.org/10.3115/976909.979640

[8] Farisi, Arif Abdurrahman, Yuliant Sibaroni, and Said Al Faraby. "Sentiment analysis on hotel reviews using Multinomial Naïve Bayes classifier." Journal of Physics: Conference Series. Vol. 1192. No. 1. IOP Publishing, 2019.https://doi.org/10.1088/1742-6596/1192/1/012024

[9] Khare, Arpit, et al. "Sentiment analysis and sarcasm detection of indian general election tweets." arXiv preprint arXiv:2201.02127 (2022).https://doi.org/10.1201/9781003320340-20

[10] Alashri, Saud, et al. "The 2016 US Presidential Election on Facebook: an exploratory analysis of sentiments." (2018).https://doi.org/10.24251/HICSS.2018.223

[11] Jianqiang, Zhao, Gui Xiaolin, and Zhang Xuejun. "Deep convolution neural networks for twitter sentiment analysis." IEEE access 6 (2018): 23253-23260.https://doi.org/10.1109/ACCESS.2017.2776930

[12] Wang, Xingyou, Weijie Jiang, and Zhiyong Luo. "Combination of convolutional and recurrent neural network for sentiment analysis of short texts." Proceedings of COLING 2016, the 26th international conference on computational linguistics: Technical papers. 2016.

[13] Chang, Victor, et al. "An improved model for sentiment analysis on luxury hotel review." Expert Systems 40.2 (2023): e12580.https://doi.org/10.1111/exsy.12580

[14] Huang, Xin, et al. "Lstm based sentiment analysis for cryptocurrency prediction." International Conference on Database Systems for Advanced Applications. Springer, Cham, 2021.https://doi.org/10.1007/978-3-030-73200-4_47

[15] Pronko, Rafał. "Simple bidirectional LSTM solution for text classification." Proceedings ofthePolEval2019Workshop (2019): 111.

[16] Krouska, Akrivi, Christos Troussas, and Maria Virvou. "The effect of preprocessing techniques on Twitter sentiment analysis." 2016 7th international conference on information, intelligence, systems & applications (IISA). IEEE, 2016.https://doi.org/10.1109/IISA.2016.7785373

[17] Hassan, Rakibul, and Md Rabiul Islam. "Impact of sentiment analysis in fake online review detection." 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD). IEEE, 2021.https://doi.org/10.1109/ICICT4SD50815.2021.9396899

[18] Shivani Wadhwani 2023. Sentiment Analysis of User Youtube Comments Using Classifier Algorithm. International Journal of Innovations in Science, Engineering And Management. 2, 1 (Feb. 2023), 25-32.