An Empirical Analysis of Twitter Reviews Using Optimal Machine Learning Techniques
Received: 8 May 2025 | Revised: 12 June 2025, 2 July 2025, 10 July 2025, 15 July 2025, and 17 July 2025 | Accepted: 19 July 2025 | Online: 26 August 2025
Corresponding author: Rohini G. Khalkar
Abstract
Sentiment analysis, a key method in Natural Language Processing (NLP), is used to recognize, extract, and classify subjective material from textual data. With the rapid development of user-generated content on social media platforms, such as Twitter, Facebook, and Instagram, sentiment analysis has gained significant importance. Social media platforms have proven to be useful for gauging customer reviews and brand perception to determine sentiments and thoughts on a variety of topics. Analyzing such data presents challenges due to the brevity of posts, informal syntax, slang, and the heavy use of emojis. This paper proposes a hybrid sentiment analysis framework that integrates textual features with emoji-based sentiment cues. A Support Vector Machine (SVM) classifier is employed along with a balancing factor to ensure vigorous classification. Support Vector Machine (SVM) is the most accurate approach for sentiment classification. Tailored preprocessing significantly improves classification accuracy by comparing traditional and Twitter-specific preprocessing methods. Feature extraction is carried out using Term Frequency-Inverse Document Frequency (TF-IDF), which captures the contextual importance of words. In addition, emoji sentiment mapping assigns predefined sentiment scores to frequently used emojis, thereby enhancing semantic understanding and enlightening the accuracy of sentiment predictions. This study demonstrates that it is important to select appropriate preprocessing and classification techniques for accurate sentiment analysis in a social media context. SVM, Logistic Regression (LR), and Naïve Bayes (NB) classifiers were applied on the sentiment140 dataset, focusing on a sentiment analysis of more than 1.5 million tweets. SVM was found to be more effective when working with a balancing factor that considers the standard deviation.
Keywords:
sentiment analysis, support vector machine, classification, opinion mining, logistic regression, standard deviationDownloads
References
G. Rao, D. G. Pujari, R. G. Khalkar, and V. A. Medhe, "Study on Software Defect Prediction Based on SVM and Decision Tree Algorithm," International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 7s, pp. 90–95, Jul. 2023. DOI: https://doi.org/10.17762/ijritcc.v11i7s.6980
R. G. Khalkar, M. S. Bewoor, S. P. Medhane, and G. Rao, "Comprehensive study of reviews from social media using machine learning techniques," in Advances in AI for Biomedical Instrumentation, Electronics and Computing, 1st ed., London: CRC Press, 2024, pp. 288–293.
S. Sorare and M. Kamble, "Ternary Classification of Product Based Reviews: Survey, Open Issues and New Approach for Sentiment Analysis," Indian Journal of Artificial Intelligence and Neural Networking, vol. 1, no. 2, pp. 1–8, Apr. 2021. DOI: https://doi.org/10.35940/ijainn.B1008.041221
M. Cliche, "BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs." arXiv, 2017. DOI: https://doi.org/10.18653/v1/S17-2094
"Sentiment140 dataset with 1.6 million tweets." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/kazanova/sentiment140.
S. Kumar, R. Sanasam, and S. Nandi, "IndiSentiment140: Sentiment Analysis Dataset for Indian Languages with Emphasis on Low-Resource Languages using Machine Translation," in Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Mexico City, Mexico, 2024, pp. 7689–7698. DOI: https://doi.org/10.18653/v1/2024.naacl-long.425
Y. Qi and Z. Shabrina, "Sentiment analysis using Twitter data: a comparative application of lexicon- and machine-learning-based approach," Social Network Analysis and Mining, vol. 13, no. 1, Feb. 2023, Art. no. 31. DOI: https://doi.org/10.1007/s13278-023-01030-x
V. Priyanka, "Twitter Sentiment Analysis using Deep Learning," SSRN Electronic Journal, 2021. DOI: https://doi.org/10.2139/ssrn.3885137
L. Jiang, M. Yu, M. Zhou, X. of the 49th A. M. of the A. for C. L. Liu, and T. Zhao, "Target-dependent Twitter Sentiment Classification," in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, Portland, OR, USA, Jun. 2011, pp. 151–160.
J. Ranganathan and A. Tzacheva, "Emotion Mining in Social Media Data," Procedia Computer Science, vol. 159, pp. 58–66, Jan. 2019. DOI: https://doi.org/10.1016/j.procs.2019.09.160
M. S. Neethu and R. Rajasree, "Sentiment analysis in twitter using machine learning techniques," in 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT), Tiruchengode, Jul. 2013, pp. 1–5. DOI: https://doi.org/10.1109/ICCCNT.2013.6726818
D. Gurkhe, N. Pal, and R. Bhatia, "Effective Sentiment Analysis of Social Media Datasets using Naive Bayesian Classification," International Journal of Computer Applications, vol. 99, no. 13, pp. 1–4, Aug. 2014. DOI: https://doi.org/10.5120/17430-8274
M. Zouidine and M. Khalil, "Large Language Models for Arabic Sentiment Analysis and Machine Translation," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 20737–20742, Apr. 2025. DOI: https://doi.org/10.48084/etasr.9584
Y. D. Al-Otaibi, "Enhancing e-Commerce Strategies: A Deep Learning Framework for Customer Behavior Prediction," Engineering, Technology & Applied Science Research, vol. 14, no. 4, pp. 15656–15664, Aug. 2024. DOI: https://doi.org/10.48084/etasr.7945
K. Divya and Mrs P. Menaka, "Twitter Sentiment Analysis," International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 11, no. 2, pp. 1305–1310, Mar. 2025. DOI: https://doi.org/10.32628/CSEIT25112465
O. Y. Adwan, M. Al-Tawil, A. Huneiti, R. Shahin, A. Abu Zayed, and R. Al-Dibsi, "Twitter Sentiment Analysis Approaches: A Survey," International Journal of Emerging Technologies in Learning (iJET), vol. 15, no. 15, Aug. 2020, Art. no. 79. DOI: https://doi.org/10.3991/ijet.v15i15.14467
E. Deniz, H. Erbay, and M. Coşar, "Multi-Label Classification of E-Commerce Customer Reviews via Machine Learning," Axioms, vol. 11, no. 9, Aug. 2022, Art. no. 436. DOI: https://doi.org/10.3390/axioms11090436
K. Sudheer and B. Valarmathi, "Real time sentiment analysis of e-commerce websites using machine learning algorithms," International Journal of Mechanical Engineering and Technology, vol. 9, pp. 180–193, Feb. 2018.
R. G. Khalkar, M. S. Bewoor, S. P. Medhane, and G. Rao, "Comprehensive study of reviews from social media using machine learning techniques," in Advances in AI for Biomedical Instrumentation, Electronics and Computing, 1st ed., London, UK: CRC Press, 2024, pp. 288–293. DOI: https://doi.org/10.1201/9781032644752-54
S. Gouthami and N. P. Hegde, "Automatic Sentiment Analysis Scalability Prediction for Information Extraction Using SentiStrength Algorithm," in Proceedings of Third International Conference on Advances in Computer Engineering and Communication Systems, vol. 612, A. B. Reddy, S. Nagini, V. E. Balas, and K. S. Raju, Eds. Springer Nature Singapore, 2023, pp. 21–30. DOI: https://doi.org/10.1007/978-981-19-9228-5_3
A. Badgaiyya, P. Shankarpale, R. Wankhade, U. Shetye, and S. Pande, “An Application of Sentiment Analysis Based on Hybrid Database of Movie Ratings,” International Research Journal of Engineering and Technology, vol. 08, no. 01, 2021.
Downloads
How to Cite
License
Copyright (c) 2025 Rohini G. Khalkar, Mrunal S. Bewoor, Sampat P. Medhane
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
