https://github.com/romanmicuda/youtube-comments-web
YouTube Comment Sentiment Analyzer is a web application that leverages a trained PyTorch model to evaluate the sentiment of YouTube comments. It provides users with real-time analysis, categorizing comments as positive, neutral, or negative, and displays the associated probabilities.
https://github.com/romanmicuda/youtube-comments-web
flask pytorch-implementation react youtube-comments
Last synced: 2 months ago
JSON representation
YouTube Comment Sentiment Analyzer is a web application that leverages a trained PyTorch model to evaluate the sentiment of YouTube comments. It provides users with real-time analysis, categorizing comments as positive, neutral, or negative, and displays the associated probabilities.
- Host: GitHub
- URL: https://github.com/romanmicuda/youtube-comments-web
- Owner: romanmicuda
- License: apache-2.0
- Created: 2025-04-01T20:32:24.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2025-04-01T22:21:10.000Z (2 months ago)
- Last Synced: 2025-04-01T22:22:30.077Z (2 months ago)
- Topics: flask, pytorch-implementation, react, youtube-comments
- Language: TypeScript
- Homepage: https://github.com/romanmicuda/youtube-comments
- Size: 2.47 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# YouTube Comments Sentiment Analyzer
A web application that analyzes the sentiment of YouTube comments using machine learning.
## Overview
This application uses a PyTorch neural network model to classify YouTube comments into different sentiment categories.
## Project Demonstration
Below is a demonstration of the YouTube Comments Sentiment Analyzer in action:

The application provides real-time sentiment analysis of comments from YouTube videos, helping content creators understand audience reactions and engagement.
## InstallationĂ¥
### Prerequisites
- Python 3.7+
- Conda (Miniconda or Anaconda)### Step 1: Clone the repository
```bash
git clone https://github.com/romanmicuda/youtube-comments-web
cd youtube-comments-web
```### Step 2: Set up a Conda environment
```bash
# Create a new conda environment
conda create -n youtube-comments python=3.8
# Activate the environment
conda activate youtube-comments
```### Step 3: Install dependencies
```bash
# Install PyTorch
conda install pytorch torchvision -c pytorch
# Install other dependencies
conda install scikit-learn flask
pip install joblib flask-cors
```### Step 4: Download pre-trained models (if available)
Place your pre-trained models and vectorizers in the appropriate directory.
## Usage
### Starting the server
```bash
python server/app.py
```### Running the frontend
```bash
# Install dependencies
cd app
yarn install# Start development server
yarn dev
```The Flask server will run on http://127.0.0.1:5000 by default.
The Next.js frontend will typically run on http://localhost:3000.## Development
### Training a new model
To train a new sentiment analysis model, refer to the training scripts in the repository.
For more details, check the [training documentation](https://github.com/romanmicuda/youtube-comments/blob/main/README.md#training).
## License
[Apache License](LICENSE)