A Majority Voting System For Reliable Sentiment Analysis Of Product Reviews
Keywords:
Product reviews, sentiment analysis, majority votingAbstract
This article examines the majority voting approach to enhance the reliability of product reviews submitted by users on online platforms and improve the accuracy of sentiment analysis results. The majority voting system determines the final sentiment label by aggregating the results produced by multiple annotators or different models. The advantages of this approach and its application areas (in the annotation process and in combining model outputs) are also examined. The article further details the working principles of the system, the process of evaluating and selecting reviews, and the impact of user votes on reliability. The majority voting approach not only enhances sentiment analysis outcomes but also helps filter out fake or biased reviews. This method is particularly noteworthy as an important methodological tool for improving dataset quality and ensuring trustworthy model outputs in developing ABSA and other linguistics-based models for the Uzbek language.
References
Maslowska E, Malthouse EC, Bernritter SF. 2017. Too good to be true: the role of online reviews’ features in probability to buy. International Journal of Advertising 36(1):142–163 DOI 10.1080/02650487.2016.1195622.
Hu, M., & Liu, B. (2004, August). Mining and summarizing customer reviews. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 168-177).
Chevalier, J. A., & Mayzlin, D. (2006). The effect of word of mouth on sales: Online book reviews. Journal of marketing research, 43(3), 345-354.
Jindal, N., & Liu, B. (2008, February). Opinion spam and analysis. In Proceedings of the 2008 international conference on web search and data mining (pp. 219-230).
Beutel, A., Xu, W., Guruswami, V., Palow, C., & Faloutsos, C. (2013, May). Copycatch: stopping group attacks by spotting lockstep behavior in social networks. In Proceedings of the 22nd international conference on World Wide Web (pp. 119-130).
Zhang, Y., & Wallace, B. (2015). A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820.
Elov, B., Abdullayev, A., & Xudayberganov, N. (2025). O ‘ZBEK TILI MATNLARINI NAIVE BAYES USULI ASOSIDA SENTIMENT TAHLIL QILISH. DIGITAL TRANSFORMATION AND ARTIFICIAL INTELLIGENCE, 3(2), 153-159.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 M. Suyunova, M. Amirqulov
This work is licensed under a Creative Commons Attribution 4.0 International License.