Successfully developed a machine learning model which can predict whether an online review is fraudulent or not. The main idea used to detect the fake nature of reviews is that the review should be computer generated through unfair means. If the review is created manually, then it is considered legal and original.

An AI-powered Fake Review Detector built with Python, Streamlit, and Scikit-learn. Uses TF-IDF vectorization, Logistic Regression, and behavioral text analytics (sentiment, exclamations, clichés) to identify synthetic or spammy product reviews. Includes training scripts and a full interactive dashboard.

Project Files for Final Year Project

Fake review detection using machine learning and deep learning techniques such as CNNs, SOMs, K-means clustering, various supervised models and natural language processing tools such as Word2Vec & TFIDF, GloVe etc.

This project related to one of my B.Tech final year project that investigates the influence of linguistic and sentiment analysis features on detecting fake reviews in e-commerce (Amazon).

Fraud, Fake News, Fake Review, Detection using AI in a extention.

Android app for spam and fake review detection.

FakeChecker is a part of my Engineering thesis project on Warsaw University of Technology. Its aim is to detect fake reviews on Google Maps.

Fake Review Detection System Using Machine Learning with source code and documents. It is full stack web application project with code and documents.

Implementation of multiple NLP approaches, in order to identify fake product reviews at one of the leader Virtual Merchants of the world.

Fake Review detection on YELP dataset

Undergraduate thesis project on pothole detection using crowd sourced reviews and smartphone sensor data and computer vision

🛒 AI-powered e-commerce intelligence platform for detecting fake reviews, tracking prices, and generating trust scores with ethical AI transparency.

Bengali/Bangla Fake Review Detection Dataset

AI-powered fake review detection using fine-tuned BERT · 96.65% accuracy · FastAPI + React

A Machine Learning powered web application to detect fake product reviews using behavioral analysis and NLP. Built with Python and Streamlit.

AI-powered system for detecting fake reviews, analyzing sentiment, and generating summaries. Combines BERT, embeddings, and deep learning to ensure trustworthy insights for e-commerce and service domains.

Our study utilizes BERT and LSTM models alongside Monte Carlo Dropout (MCD) on the Yelp Labelled Dataset. MCD bolsters robustness by introducing uncertainty through neuron dropout. The BERT-embedded MCD achieves an impressive 91.75% accuracy, surpassing the LSTM model.

🔍 Detect fake product reviews using NLP techniques, TF-IDF, and Logistic Regression, with an interactive Streamlit app for real-time predictions.