https://github.com/johnit56/commentsense
CommentSense is an intelligent tool that leverages OpenAI’s Large Language Models (LLMs) to analyze YouTube comments and generate high-level feedback for content creators. Just paste a YouTube link, and CommentSense will summarize what your audience thinks — the good, the bad, and what they want next.
https://github.com/johnit56/commentsense
ai comment-analysis content-feedback gpt-4 llm nlp openai sentiment-analysis video-insights youtube
Last synced: about 2 months ago
JSON representation
CommentSense is an intelligent tool that leverages OpenAI’s Large Language Models (LLMs) to analyze YouTube comments and generate high-level feedback for content creators. Just paste a YouTube link, and CommentSense will summarize what your audience thinks — the good, the bad, and what they want next.
- Host: GitHub
- URL: https://github.com/johnit56/commentsense
- Owner: johnIT56
- License: mit
- Created: 2025-05-20T12:50:40.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-20T13:44:09.000Z (about 1 year ago)
- Last Synced: 2025-06-22T00:04:59.997Z (about 1 year ago)
- Topics: ai, comment-analysis, content-feedback, gpt-4, llm, nlp, openai, sentiment-analysis, video-insights, youtube
- Language: Python
- Homepage:
- Size: 251 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# CommentSense: AI-Powered YouTube Comment Analyzer for Creators 🎥
**CommentSense** is an intelligent tool that leverages OpenAI’s Large Language Models (LLMs) to **analyze YouTube comments** and generate high-level feedback for content creators. Just paste a YouTube link, and CommentSense will summarize what your audience thinks — the good, the bad, and what they want next.
> Designed for creators, brand strategists, and YouTube growth hackers.
---
## Features
- Input any **YouTube video link**
- Automatically fetches **comments** using the **YouTube Data API**
- Uses **OpenAI GPT** to analyze:
- ✅ Overall audience sentiment
- ✅ Strengths of the video
- ✅ Weaknesses or pain points
- ✅ Suggestions or requests from viewers
- Outputs clean, structured insights
- Visualized with **Gradio UI**
---
## Use Cases
- **Content Creators** – Understand viewer feedback and plan better content
- **Marketing Teams** – Gauge brand reception and viewer language
- **Researchers** – Track sentiment trends and audience behavior
- **Developers** – Build custom tools around YouTube engagement
---
## How It Works
1. User enters a YouTube video URL
2. Tool extracts the video ID
3. Fetches up to 100 top-level comments using the **YouTube Data API v3**
4. Sends comment list to **OpenAI GPT-4** with the following prompt:
```python
system_message = "You are an assistant that analyses YouTube comments"
user_prompt = f"""Analyse the following comments and tell the channel owner:
1. Overall audience sentiment
2. Strengths of the video
3. Weaknesses
4. Future content demands or suggestions from viewers.
Comments: {comments_list}
```
5. Returns a structured analysis for the creator to act on.
---
## 🛠️ Installation
```bash
git clone https://github.com/johnIT56/CommentSense.git
cd CommentSense
pip install -r requirements.txt
python app.py
```
You’ll need a YouTube Data API key and an OpenAI API key set up in your environment or a config file.
---
Contributing
Contributions are welcome! Please open issues or pull requests to improve functionality, UI, or model prompts.
---
License
MIT License
---
Contact
Built with 💡 by johnIT56