An Ensemble of Naive Bayes Variants and SentiWordNet with Threshold Adjustment for Aspect Based Sentiment Analysis on Restaurant Reviews


Authors : Musa Karatu; Hamza Abdullahi Kwazo

Volume/Issue : Volume 11 - 2026, Issue 2 - February

Google Scholar : https://tinyurl.com/3ty69r8s

Scribd : https://tinyurl.com/k9kdacz7

DOI : https://doi.org/10.38124/ijisrt/26feb1207

PlumX Metrics

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This study proposes an enhanced framework for Aspect-Based Sentiment Analysis (ABSA) applied to restaurant reviews by integrating SentiWordNet with the variants of Naïve Bayes classifier. Existing sentiment analysis techniques often focus on limited aspects such as food quality, service, and price, while overlooking menu variety, which significantly influences customer perceptions. A dataset of 10,000 restaurant reviews was pre-processed using text normalization, tokenization, lemmatization, and stop-word removal. Aspect extraction was conducted through supervised learning with Naïve Bayes, and sentiment polarity scores were assigned using SentiWordNet. To handle mixed feature types, an ensemble combining Multinomial Naïve Bayes for TF-IDF features and Gaussian Naïve Bayes for sentiment polarity features was employed. Experimental results demonstrate that the proposed model achieves 88% accuracy with improved F1-scores for both positive and negative classes compared to baseline approaches. This contribution provides more balanced classification and offers practical insights for restaurant managers to enhance customer satisfaction. The findings highlight the significance of menu variety as a critical aspect of dining experiences. Future work may extend this research by applying deep learning models and multilingual datasets to broaden applicability.

Keywords : Aspect-Based Sentiment Analysis, Natural Language Processing, SentiWordNet, Naïve Bayes, Restaurant Reviews, Customer Satisfaction.

References :

  1. Rita, P.; Vong, C.; Pinheiro, F.; Mimoso, J. A sentiment analysis of Michelin-starred restaurants. EJMBE 2022, 32, 276-295.
  2. Pan, M.; Li, N.; Huang, X. Asymmetrical impact of service attribute performance on consumer satisfaction: an asymmetric impact-attention-performance analysis. . Inf Technol Tourism 2022, 4, 221-243.
  3. Hossain, N.; Bhuiyan, M.R.; Tumpa, Z.N. Sentiment Analysis of Restaurant Reviews using Combined CNN-LSTM. 2020, 1-6.
  4. Luo, M.; Mu, X. A New Ontology for restaurant Review Sentiment Analysis. Proceedinds of the Association for information Science and Technology 2023, 60, 1068-1070.
  5. Amalia, P.R.; Winarko, E. Aspect-based sentiment analysis on indonesian  restaurant review using a combination of convolutional neural network and contextualized word embedding. . IJCCS (Indonesian Journal of Computing and Cybernetics Systems) 2021, 15, 285-294.
  6. Abdullah, R.; Suhariyanto; Sarno, R. Aspect Based Sentiment Analysis for Explicit and Implicit Aspects in Restaurant Review using Grammatical Rules, Hybrid Approach, and SentiCircle. International Journal of Intelligent Engineering & System 2021, 295-305. .
  7. Nurifan, F.; Sarno, R.; Sungkono, K.R. Aspect based sentiment analysis for restaurant reviews using hybrid elmo-wikipedia and hybrid expanded opinion lexicon-senticircle. . International Journal of Intelligent Engineering and Systems 2019, 12, 47-58. .
  8. Govindarajan, M. Sentiment Analysis of Restaurant review using Hybrid classification method. . In Proceedings of the Proceedings of 2nd IRF International Conference, 2014; pp. 127-133.
  9. Aye, Y.M.; Aung, S.S. Sentiment Analysis for Reviews of Restaurant in Myanmar Text. IEE COMPUTER SOCIETY 2017, 321-326.
  10. Adnan, M.; Sarno, R.; Sungkono, M. Sentiment Analysis of Restaurant Review with Classification Approach in the Decision Tree-J48 Algorithm. 2019, 121-126.
  11. Sharif, O.; Hoque, M.M.; Hossain, E. Sentiment Analysis of Bengali Texts on Online Restaurant Reviews Using Multinomial Na¨ıve Bayes. 1st International Conference on Advances in Science, Engineering and Robotics Technology 2019, 1-6.
  12. Hossain, N.; Bhuiyan, M.R.; Tumpa, Z.N. Sentiment Analysis of Restaurant Reviews using Combined CNN-LSTM. . 2020, 1-6.
  13. Ara, J.; Hasan, M.T.; Omar, A.A.; Bhuiyan, H. Understanding Customer Sentiment: Lexical Analysis of Restaurant Reviews. In Proceedings of the 2020 IEEE Region 10 Symposium (TENSYMP), 2020; pp. 295-299.
  14. Abdullah, R.; Suhariyanto; Sarno, R. Aspect Based Sentiment Analysis for Explicit and Implicit Aspects in Restaurant Review using Grammatical Rules, Hybrid Approach, and SentiCircle. International Journal of Intelligent Engineering & System 2021, 295-305.
  15. Eidul, T.S.; Imran, M.A.; Das, A.K. Restaurant Review Predictionusing Machine Learning and Neural Network. International Journal of Innovative Science and Research Technology 2022, 7, 1388-1392.
  16. Eidul, T.S.; Imran, M.A.; Das, A.K. Restaurant Review Predictionusing Machine Learning and Neural Network.  . International Journal of Innovative Science and Research Technology 2022, 7, 1388-1392.
  17. Aruna, M.T.; Devi, P.M.; RenukaSai, M.; Raju, T.G.; Patchimala, M.C.; Kumar, K.S. Sentiment analysis for zomata using user comments review. UGC Care Group I Journal 2023, 13, 172-176.
  18. Gujrati, M.S.; Tahakik, S.S.; Nahar, S.S.; Gujar, D.S.N. Sentiment analysis of restaurant reviews using machine learning. . International Research Journal of Modernization in Engineering Technology and Science 2023, 5, 8369-8372. .
  19. Fragko, N.; Liapakis, A.; Ntaliani, M.; Ntalianis, F.; Costopoulou, C. A Sentiment Analysis Approach for Exploring CustomerReviews of Online Food Delivery Services. A Greek Case. PREPRINT 2024, 1-14.
  20. Kaggle. restaurant-reviews. Available online: https://www.kaggle.com/datasets/joebeachcapital/restaurant-reviews (accessed on March 15).
  21. Pant, V.K.; Sharma, R.; Kundu, S. An overview of stemming and lemmatization techniques. Advances in Networks, Intelligence and Computing 2024, 308-321.
  22. Kan, Z.; Luliang, T.; Jie, G.; Chang, R.; Zhang, X.; Xue, Y. Detecting and evaluating urban clusters with spatiotemporal big data. Sensors 2019, 19, 461.
  23. Rajeswari, A.; Mahalakshmi, M.; Nithyashree, R.; Nalini, G. Sentiment analysis for predicting customer reviews using a hybrid approach. In Proceedings of the 2020 Advanced Computing and Communication Technologies for High Performance Applications (ACCTHPA), 2020; pp. 200-205.
  24. Sijtsma, K.; Emons, W. Nonparametric statistical methods. International encyclopedia of education 2010, 7, 347-353.

This study proposes an enhanced framework for Aspect-Based Sentiment Analysis (ABSA) applied to restaurant reviews by integrating SentiWordNet with the variants of Naïve Bayes classifier. Existing sentiment analysis techniques often focus on limited aspects such as food quality, service, and price, while overlooking menu variety, which significantly influences customer perceptions. A dataset of 10,000 restaurant reviews was pre-processed using text normalization, tokenization, lemmatization, and stop-word removal. Aspect extraction was conducted through supervised learning with Naïve Bayes, and sentiment polarity scores were assigned using SentiWordNet. To handle mixed feature types, an ensemble combining Multinomial Naïve Bayes for TF-IDF features and Gaussian Naïve Bayes for sentiment polarity features was employed. Experimental results demonstrate that the proposed model achieves 88% accuracy with improved F1-scores for both positive and negative classes compared to baseline approaches. This contribution provides more balanced classification and offers practical insights for restaurant managers to enhance customer satisfaction. The findings highlight the significance of menu variety as a critical aspect of dining experiences. Future work may extend this research by applying deep learning models and multilingual datasets to broaden applicability.

Keywords : Aspect-Based Sentiment Analysis, Natural Language Processing, SentiWordNet, Naïve Bayes, Restaurant Reviews, Customer Satisfaction.

Paper Submission Last Date
31 - March - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe