<<<<<<< HEAD

🎥 YouTube Sentiment Intelligence Platform

=======

A full-stack, creator-focused analytics platform that analyzes YouTube video comments to understand audience sentiment, engagement quality, and behavioral trends.

Built with a modern React + Tailwind SaaS UI and a Python Flask analytics backend, this project goes beyond basic sentiment analysis by adding spam detection, audience mood scoring, sentiment timelines, and creator insights — all powered by VADER (NLTK) and real YouTube data.

---

🚀 Key Features

🔗 Video Analysis

• Submit any public YouTube video link
• Fetch comments using YouTube Data API v3
• Cache comments in MongoDB for reuse and performance

🤖 Sentiment Intelligence (VADER)

• Classifies comments as Positive / Neutral / Negative
• Uses compound sentiment scores for weighted analysis
• Fully explainable logic (no black-box ML models)

🧹 Spam & Bot Detection

• Detects:
  • Duplicate comments
  • Emoji spam
  • Link-based spam
• Spam comments are excluded from analytics

📊 Creator-Focused Insights

• Audience Mood Score (weighted by likes)
• Top Positive Comments (what viewers loved)
• Comments Needing Attention (negative / critical feedback)
• Spam Percentage per video

📈 Sentiment Over Time

• Tracks sentiment day-by-day
• Detects sentiment shifts and spikes
• Useful for identifying reactions to viral moments

📊 Visual Analytics

• Sentiment distribution:
  • Bar Chart
  • Pie Chart
• Clean, professional dashboards

👤 Channel & Video Metadata

• Channel name, description, subscribers
• Video views, likes, and comment count

---

🎨 UI & UX

• Dark, premium SaaS-style interface
• Animated gradients & glassmorphism
• Creator dashboards:
  • Home
  • Analyze
  • Insights
  • Sentiment Timeline
• Fully responsive (desktop & mobile)

---

Results

🧱 Tech Stack

🖥 Frontend

• React.js
• Tailwind CSS
• Vite
• React Router

🔥 Backend

• Python 3.10+
• Flask + Flask-CORS
• NLTK (VADER SentimentIntensityAnalyzer)
• Google YouTube Data API v3
• MongoDB (PyMongo)
• Pandas & NumPy
• Plotly (chart generation)

---

⚙️ Setup Instructions

🔧 Prerequisites

• Node.js v18+
• Python 3.10+
• MongoDB (local or Atlas)
• Google Developer Account
• YouTube Data API key

---

📁 Clone the Repository

git clone https://github.com/Manu839/Youtube-sentiment-analysis.git
cd yt-sentiment-analysis

📦 Backend Setup (Flask)

🔹 Navigate to backend directory:

cd backend
python -m venv env
source env/bin/activate   # Or: env\Scripts\activate on Windows
pip install -r requirements.txt

🔹 Set your API Key

• DEVELOPER_KEY=YOUR_YOUTUBE_API_KEY_HERE
• MONGO_URI=mongodb://localhost:27017 # Or your MongoDB Atlas URI
• MONGO_DB=yt_sentiment

🔹 Run the Flask server

python app.py

• Server will run at: http://localhost:5000

🌐 Frontend Setup (React + Vite)

🔹 Navigate to frontend directory:

cd frontend
npm install
npm run dev

Frontend runs at: http://localhost:5173

🐛 Troubleshooting

• 403 commentsDisabled → Video has comments disabled

• 500 errors → Check API key & quota limits

• Insights not showing → Analyze a video first

• CORS issues → Ensure Flask-CORS is enabled

• MongoDB errors → Confirm MongoDB is running

React + Vite

This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.

Currently, two official plugins are available:

• @vitejs/plugin-react uses Babel for Fast Refresh
• @vitejs/plugin-react-swc uses SWC for Fast Refresh

Expanding the ESLint configuration

If you are developing a production application, we recommend using TypeScript with type-aware lint rules enabled. Check out the TS template for information on how to integrate TypeScript and typescript-eslint in your project.