Login Search
FMDB Transactions on Sustainable Critical Infrastructures Submit Paper
    Crossref logo

    Archiving

    Portico

    Fernando Martins De Bulhão is a member of

    Crossref logo

A Comparative Evaluation of Machine Learning Models for Fake Online Review Detection

Authors:
Khin Shin Thant, Myat Mon Khaing, Thet Thet Aung, Hlaing Htake Khaung Tin, Aygul Z. Ibatova, Bipul Magar

Addresses:
Faculty of Information Science, Polytechnic University, Dawei, Tanintharyi, Myanmar. Faculty of Information Science, Polytechnic University, Myeik, Tanintharyi, Myanmar. Faculty of Information Science, University of Information Technology, Yangon, Myanmar. Department of Social Sciences and Humanities, Industrial University of Tyumen, Tyumen, Russia. Department of Information Technology, University of Sunshine Coast, Sippy Downs, Queensland, Australia.

Abstract:

E-commerce and review websites are becoming increasingly popular, which means that customer reviews are becoming an increasingly valuable data source when it comes to making purchasing decisions. As the tendency to post false reviews grows, consumers may become confused, businesses may suffer reputational damage, and consumers' trust in online marketplaces may erode. This research compares machine learning methods for detecting fake internet reviews. The preprocessing steps include text cleaning, tokenization, feature extraction, and transformation. The dataset also includes both honest and dishonest reviews. The study develops several machine learning classifiers, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosting, to determine which is most effective at identifying fake reviews. When comparing machine learning models, the study considers metrics such as accuracy, precision, recall, F1 score and ROC AUC. To determine which machine learning approach best addresses the issue, the study examines the benefits and drawbacks of each approach.

Keywords: Fake Online Reviews; Machine Learning; Deceptive Review Detection; Sentiment Analysis and E-Commerce; Classification Models; Review Fraud.

Received on: 09/10/2025, Revised on: 02/12/2025, Accepted on: 25/01/2026, Published on: 03/06/2026

DOI: 10.69888/FTSCIS.2026.000765

FMDB Transactions on Sustainable Critical Infrastructures, 2026 Vol. 1 No. 2, Pages: 98-107

  • Views : 96
  • Downloads : 12
Download PDF