Real-Time Fake Review Detection System using NLP and Machine Learning

Authors:

Kartik Patidar

Department of Artificial Intelligence and Machine Learning Madhav Institute of Technology and Science

Gwalior, Madhya Pradesh, India Email: patidarkartik575@gmail.com

Abstract — The rapid expansion of e-commerce platforms such as Amazon, Flipkart, and Yelp has made online reviews a crucial factor in influencing customer decisions. However, the growing presence of fake reviews has significantly reduced trust in these platforms. Fake reviews are often generated to manipulate product ratings and mislead users, creating challenges for both consumers and businesses. Traditional manual moderation techniques are inefficient and fail to handle large-scale data streams in real time. This paper proposes a real-time fake review detection system using Natural Language Processing (NLP) and Machine Learning (ML) techniques. The system processes review text through preprocessing steps such as tokenization, stop-word removal, stemming, and lemmatization. Feature extraction techniques like TF-IDF and word embeddings are used to convert textual data into numerical form. Machine learning classifiers including Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), and Random Forest are applied for classification. The system is designed for real-time detection, ensuring immediate identification of fake reviews. Experimental analysis shows that hybrid NLP-ML models achieve high accuracy, precision, and recall, making them suitable for deployment in large-scale e-commerce environments. The proposed approach enhances transparency, improves customer trust, and strengthens the reliability of online review systems.

Keywords — Fake Review Detection, NLP, Machine Learning, TF-IDF, Real-Time System, E-commerce Security, Text Classification