Fake Review Detection System using NLP and ML

Fake Review Detection System using NLP and ML

 Introduction

These days, when people shop online, product reviews really help them decide what to buy. But some reviews are fake either to make a product look better or to harm others.To solve this problem, we made a Fake Review Detection System using NLP and Machine Learning. It comes with an easy-to-use web app made with Streamlit.Users can upload a CSV file with product reviews, and the system will check them. Then, it gives two download files one with real reviews and one with fake ones.

What You Will Learn

• How to preprocess review data
• How to train an NLP-based ML model
• How to classify fake vs. real reviews
• How to create a web interface using Streamlit
• How to handle file upload and download in a web app

Heart Attack Prediction Using Machine Learning :

Tech Stack

• Frontend: Streamlit (Python-based web framework)
• Backend: Logistic Regression with TF-IDF Vectorizer
• Language: Python
• Libraries: Pandas, NumPy, scikit-learn, re, string

Streamlit App Flow

1. Upload the CSV file

Users upload a CSV containing product review data.

2. NLP Model Processes Reviews

The system preprocesses the text (lowercasing, punctuation and digit removal) and uses a pre-trained TF-IDF + Logistic Regression model to classify reviews.

3. Download the Results

Two downloadable CSVs are generated: real_reviews.csv and fake_reviews.csv.

New Real World Projects : Click Here

Required CSV Format

Ensure your file follows this structure:

• category: Product category
• rating: Star rating (1-5)
• label: CG for genuine, OR for other
• text_: The review content

How Fake/Real Is Determined

We used TF-IDF (Term Frequency-Inverse Document Frequency) to transform text data into numerical vectors. Then, we trained a Logistic Regression model using labeled data:

• Label CG is treated as real (1)
• Others are treated as fake (0)

Full Streamlit Code Overview

The app is a single Python file:

• Loads and trains a model using a sample dataset
• Allows CSV upload
• Validates column structure
• Preprocesses text
• Classifies reviews
• Generates download buttons for real and fake reviews

How to Run the App

1. Save the app as fake_review_app.py
2. Install dependencies:

pip install streamlit pandas numpy scikit-learn

3. Run the Streamlit app:

streamlit run fake_review_app.py

4. Open your browser at
5. Upload your review CSV and download results!

Report Structure

Abstract

• Short summary of the project (100200 words).

• Should include objective, methodology (ML/Deep Learning/Tools), and key results.

Introduction

• Overview: General context (e.g., healthcare, environment, salary prediction, etc.).

• Problem Statement: The main issue being solved.

• Motivation: Why this project is important and useful.

Literature Review

• Previous works, research papers, or existing studies in the same area.

• Comparisons of different approaches.

• Gaps in existing research that your project addresses.

Existing System & Drawbacks

• How current systems/methods work.

• Their limitations (accuracy, scalability, cost, user experience, etc.).

Proposed System

• Description of your solution.

• Features, advantages, and innovations over existing system.

System Architecture (Diagrams)

• High-level architecture diagram.

• Data flow diagram (DFD).

• Use-case diagram (if needed).

System Specifications

• Hardware Requirements: CPU, RAM, GPU, Storage.

• Software Requirements: OS, Python, Libraries, Frameworks, Database.

Experimental Design Diagrams

• Workflow diagrams showing data preprocessing, training, testing, and prediction pipeline.

• Flowchart/ER diagram (if using database).

Implementation

• Setup process (environment installation).

• Explanation of modules.

• Sample code snippets with explanation.

System Testing

• Types of testing done (Unit, Integration, System, User testing).

• Test cases and results.

Results & Screenshots

• Output graphs, charts, prediction results.

• Screenshots of web/app interface.

Conclusion & Future Scope

• Summary of achievements.

• Limitations of the project.

• Future improvements (adding more features, real-time deployment, cloud integration).

References

• Research papers, articles, official documentation, datasets.

• Follow IEEE or APA referencing style.