Comparative Analysis of Sentiment Analysis Dictionaries: Evaluating the Performance of NLTK, SentiWordNet, TextBlob, and VADER on Hotel Review Sentiment Classification

Abstract

Sentiment analysis is a critical task for understanding customer opinions and improving service quality in the hospitality industry. This study evaluates the performance of various sentiment analysis dictionaries, including NLTK, SentiWordNet, TextBlob, and VADER, on the task of sentiment classification of hotel reviews. Using a comprehensive dataset of hotel reviews, we preprocess the data and implement these dictionaries for sentiment classification. The performance of each dictionary is assessed using metrics such as accuracy, precision, recall, and F1-score. Our findings provide insights into the effectiveness of these dictionaries and highlight the most suitable approaches for sentiment analysis in the hospitality industry.

Introduction

This research compares four sentiment analysis dictionaries—NLTK, SentiWordNet, TextBlob, and VADER—to classify sentiments in hotel reviews, aiming to find the most effective tool for the hospitality industry. Sentiment analysis helps businesses understand customer feedback by categorizing text as positive, negative, or neutral.

Using a dataset of hotel reviews, the study preprocesses text data and evaluates each dictionary’s performance based on accuracy, precision, recall, and F1-score. Results show that VADER outperforms the others, achieving the highest accuracy (81.3%) and best balance of precision and recall, followed by TextBlob, NLTK, and SentiWordNet.

This work fills a gap in sentiment analysis research focused specifically on hotel reviews and provides practical insights for improving service quality through better sentiment classification.

Conclusion

This study presents a comparative analysis of sentiment analysis dictionaries for sentiment classification of hotel reviews. Our findings indicate that VADER is the most effective dictionary, followed closely by TextBlob. NLTK and SentiWordNet also perform reasonably well but are slightly less accurate and precise. B. Future Work Future research could explore the integration of these dictionaries with machine learning models to enhance sentiment analysis performance. Additionally, aspect-based sentiment analysis and real-time sentiment classification are promising areas for further investigation.

References

[1] Hutto, Clayton, and Eric Gilbert. \"Vader: A parsimonious rule-based model for sentiment analysis of social media text.\" In Proceedings of the international AAAI conference on web and social media, vol. 8, no. 1, pp. 216-225. 2014. [2] Bonta, Venkateswarlu, Nandhini Kumaresh, and Naulegari Janardhan. \"A comprehensive study on lexicon based approaches for sentiment analysis.\" Asian Journal of Computer Science and Technology 8, no. S2 (2019): 1-6. [3] Al-Otaibi, Shaha T., and Amal A. Al-Rasheed. \"A review and comparative analysis of sentiment analysis techniques.\" Informatica 46, no. 6 (2022). [4] Ali, Hafiz Muhammad Usman, Qaisar Farooq, Azhar Imran, and Khalil El Hindi. \"A systematic literature review on sentiment analysis techniques, challenges, and future trends.\" Knowledge and Information Systems (2025): 1-68. [5] Kumar, Sudhanshu, Partha Pratim Roy, Debi Prosad Dogra, and Byung-Gyu Kim. \"A comprehensive review on sentiment analysis: Tasks, approaches and applications.\" arXiv preprint arXiv:2311.11250 (2023). [6] Mahmoudi, Amin, Dariusz Jemielniak, and Leon Ciechanowski. \"Assessing accuracy: a study of lexicon and rule-based packages in R and python for sentiment analysis.\" IEEE Access 12 (2024): 20169-20180. [7] Xu, Guixian, Ziheng Yu, Haishen Yao, Fan Li, Yueting Meng, and Xu Wu. \"Chinese text sentiment analysis based on extended sentiment dictionary.\" IEEE access 7 (2019): 43749-43762. [8] Nguyen, Heidi, Aravind Veluchamy, Mamadou Diop, and Rashed Iqbal. \"Comparative study of sentiment analysis with product reviews using machine learning and lexicon-based approaches.\" SMU Data Science Review 1, no. 4 (2018): 7. [9] Ahmed, Murtadha, Qun Chen, and Zhanhuai Li. \"Constructing domain-dependent sentiment dictionary for sentiment analysis.\" Neural Computing and Applications 32 (2020): 14719-14732. [10] Cruz, Laura, José Ochoa, Mathieu Roche, and Pascal Poncelet. \"Dictionary-based sentiment analysis applied to a specific domain.\" In Annual International Symposium on Information Management and Big Data, pp. 57-68. Cham: Springer International Publishing, 2015. [11] Gunasekaran, Karthick Prasad. \"Exploring sentiment analysis techniques in natural language processing: A comprehensive review.\" arXiv preprint arXiv:2305.14842 (2023). [12] Chaithra, V. D. \"Hybrid approach: naive bayes and sentiment VADER for analyzing sentiment of mobile unboxing video comments.\" International Journal of Electrical and Computer Engineering (IJECE) 9, no. 5 (2019): 4452-4459. [13] Palwe, Yash Sanjay. \"Hybrid Classifier for Analyzing Customer Satisfaction.\" PhD diss., Dublin, National College of Ireland, 2021. [14] Khoo, Christopher SG, and Sathik Basha Johnkhan. \"Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons.\" Journal of Information Science 44, no. 4 (2018): 491-511. [15] Bashiri, Hadis, and Hassan Naderi. \"LexiSNTAGMM: an unsupervised framework for sentiment classification in data from distinct domains, synergistically integrating dictionary-based and machine learning approaches.\" Social Network Analysis and Mining 14, no. 1 (2024): 102. [16] Kwon, Wooseok. \"Reading customers’ minds through textual big data: Challenges, practical guidelines, and proposals.\" International Journal of Hospitality Management 111 (2023): 103473. [17] Abiola, Odeyinka, Adebayo Abayomi-Alli, Oluwasefunmi Arogundade Tale, Sanjay Misra, and Olusola Abayomi-Alli. \"Sentiment analysis of COVID-19 tweets from selected hashtags in Nigeria using VADER and Text Blob analyser.\" Journal of Electrical Systems and Information Technology 10, no. 1 (2023): 5. [18] Mërgim, H., and Jaumin AJDARI. \"SENTIMENT ANALYSIS USING THE VADER MODEL FOR ASSESSING COMPANY SERVICES BASED ON POSTS ON SOCIAL MEDIA.\" DOI: 10.2478/seeur-2023-0043 [19] Samuel, Jim, Gavin Rozzi, and Ratnakar Palle. \"The dark side of sentiment analysis: An exploratory review using lexicons, dictionaries, and a statistical monkey and chimp.\" Dictionaries, and a Statistical Monkey and Chimp (January 6, 2022) (2022). [20] Eng, Titya, Md Rashed Ibn Nawab, and Kazi Md Shahiduzzaman. \"Improving accuracy of the sentence-level lexicon-based sentiment analysis using machine learning.\" International Journal of Scientific Research in Computer Science Engineering and Information Technology 3307 (2021): 57-68.

Copyright

Copyright © 2025 Bharti Balande, Suryakant Revate. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.