Skip to content

README.md

Latest commit

 

History

History
139 lines (100 loc) · 2.64 KB

README.md

File metadata and controls

139 lines (100 loc) · 2.64 KB
Raw

VeriScope

📰 TrustLens – Fake News, Bias & Comparison Platform

TrustLens is an AI-powered web application that helps users verify the authenticity of news articles, detect political and emotional bias, and compare the same story across multiple sources — all in one place.

“Don’t just read the news. Understand it.”

🚀 Features

🔍 Fake News Detection

  • Classifies articles as Real / Misleading / Fake
  • Provides a confidence score
  • Highlights suspicious phrases

⚖️ Bias Detection

  • Political bias: Left / Right / Neutral
  • Emotional bias: Fear, anger, joy, sadness, neutral
  • Linguistic bias: Clickbait, exaggeration, loaded words

🔄 Multi-Source News Comparison

Finds the same story from multiple publishers Compares:

  • Headlines
  • Tone
  • Claims
  • Missing information
  • Shows how narratives differ

📊 Trust Score

** A final score (0–100) based on: ** Accuracy Bias neutrality Source credibility Emotional manipulation

🧠 Explainable AI

Instead of just showing numbers, TrustLens explains:

Why this article may be misleading ? What language is manipulative ? What other sources say ?

🛠 Tech Stack (Free & Open Source)

Frontend

React / Next.js Tailwind CSS Chart.js / Recharts

Backend

Python FastAPI / Flask

AI / NLP

HuggingFace Transformers spaCy TextBlob Scikit-learn

APIs

GNews API (Free tier) NewsAPI (Free tier) Web scraping (fallback)

Hosting

Frontend: Vercel / Netlify Backend: Render / Railway

🧩 System Architecture Frontend (React) ↓ Backend API (FastAPI) ↓ AI Models (NLP) ↓ News APIs + Scrapers

🧪 How It Works

User pastes a news article link or text Backend extracts and cleans the content

AI models analyze:

Authenticity Political bias Emotional tone

System fetches similar news from other sources

Articles are compared A final trust score is calculated Results are displayed with explanations

🖥 Installation (Local Setup)

  1. Clone the repository
    git clone https://github.com/your-username/trustlens.git
    cd trustlens

  2. Frontend Setup
    cd frontend
    npm install
    npm run dev

  3. Backend Setup
    cd backend
    python -m venv env
    source env/bin/activate # On Windows: env\Scripts\activate
    pip install -r requirements.txt
    python app.py

🎯 Why This Project Matters

Misinformation affects:

  1. Elections
  2. Public opinion
  3. Mental health
  4. Social harmony

TrustLens promotes: ✅ Transparency ✅ Critical thinking ✅ Media literacy ✅ Responsible AI

⚠️ Disclaimer

TrustLens does not censor content. It provides analysis, not authority. Final judgment is always left to the user.