Sentiment Analysis of Customer Reviews on E-commerce Platforms: A Machine Learning Approach

Muhammad Haroon, Zaheer Alam, Rukhsana Kousar, Jawad Ahmad and Fawad Nasim
Additional contact information
Muhammad Haroon: Faculty of Computer Science and Information Technology, Superior University, Pakistan
Zaheer Alam: Faculty of Computer Science and Information Technology, Superior University, Pakistan
Rukhsana Kousar: Faculty of Computer Science and Information Technology, Superior University, Pakistan
Jawad Ahmad: Faculty of Computer Science and Information Technology, Superior University, Pakistan
Fawad Nasim: Faculty of Computer Science and Information Technology, Superior University, Pakistan

Bulletin of Business and Economics (BBE), 2024, vol. 13, issue 3, 230-238

Abstract: Internet users are a huge segment of the consumer market, and businesses nowadays are trying to enter e-commerce, where customers leave reviews regarding products and services. Sentiment analysis is the process of extracting the customer's real feelings from the reviews of the product or services. This study compares logistic regression, naive Bayes, neural networks, and support vector machine algorithms for sentiment analysis and finds the best-performing classifiers among them. This applied study evaluates the classifiers using accuracy, precision, recall, and F1-score metrics. The dataset was taken from the E-Commence website, on which NLP and other classifiers are employed. The results show that the Naive Bayes model, with 94% accuracy, outperforms the different classifiers, where Logistic Regression and Neural Networks are at a similar level of 93%. In comparison, the SVM gave us an average of about 92%. This study suggests the significance of continuously updating sentiment analysis systems to maintain accuracy and relevance. Real-time sentiment analysis tools are a good technique for any text mining work that can help companies address customer problems based on immediate feedback and improve their products.

Keywords: E-Commerce; Logistic Regression; Naive Bayes; Neural Networks; Sentiment Analysis; SVM (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://bbejournal.com/BBE/article/view/908/1069 (application/pdf)
https://bbejournal.com/BBE/article/view/908 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rfh:bbejor:v:13:y:2024:i:3:p:230-238

DOI: 10.61506/01.00480

Access Statistics for this article

Bulletin of Business and Economics (BBE) is currently edited by Dr. Muhammad Irfan Chani

More articles in Bulletin of Business and Economics (BBE) from Research Foundation for Humanity (RFH) Contact information at EDIRC.
Bibliographic data for series maintained by Dr. Muhammad Irfan Chani ().