doi: 10.18178/joebm.2026.14.4.968
Sentiment Analysis and Machine Learning-based Classification of Online Consumer Reviews
Xinye Zhou
- Business School, Geely University, Chengdu, China
- Manuscript received August 28, 2026
- accepted October 21, 2026
- published November 10, 2026
Abstract
With the development of electronic commerce and online service systems, consumer evaluations have become an important way to evaluate the quality of products and service experiences. Because of the characteristics of online reviews such as their large number, complex structures and various emotional expressions, this paper studies the sentiment classification of consumer reviews by applying machine learning techniques. First, the 5000 online consumer reviews are processed by eliminating the noise, segmenting the words and deleting the stop-words, and then the TF-IDF method is used to convert the texts into numerical features. Then, Support Vector Machines (SVM) are used as the main classification algorithm to classify the reviews into positive and negative sentiments. Additionally, Logistic Regression and Naive Bayes are introduced as traditional machine learning methods for a comparison. The experimental results demonstrate that the SVM obtains Accuracy, Precision, Recall and F1-Score of 91.27%, 91.54%, 90.76% and 91.15% respectively, which indicates its excellent comprehensive classification ability compared with the other two comparative algorithms. The research suggests that the combination of TF-IDF and SVM can effectively identify the basic sentiments of online consumer reviews, providing useful advice for the analysis of customer feedback and service improvement.
Keywords
- online consumer reviews
- sentiment analysis
- TF-IDF
- support vector machines
- machine learning
How to Cite
Xinye Zhou, "Sentiment Analysis and Machine Learning-based Classification of Online Consumer Reviews," Journal of Economics, Business and Management, vol. 14, no. 4, pp. 352-355, 2026. https://doi.org/10.18178/joebm.2026.14.4.968
Copyright & License
Copyright © 2026 by the authors. 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 (CC BY 4.0).