{"id":28471550,"url":"https://github.com/johnit56/commentsense","last_synced_at":"2026-05-07T17:38:52.368Z","repository":{"id":294451098,"uuid":"987010664","full_name":"johnIT56/CommentSense","owner":"johnIT56","description":"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.","archived":false,"fork":false,"pushed_at":"2025-05-20T13:44:09.000Z","size":257,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-22T00:04:59.997Z","etag":null,"topics":["ai","comment-analysis","content-feedback","gpt-4","llm","nlp","openai","sentiment-analysis","video-insights","youtube"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/johnIT56.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-20T12:50:40.000Z","updated_at":"2025-05-20T13:44:12.000Z","dependencies_parsed_at":"2025-05-20T22:16:56.979Z","dependency_job_id":null,"html_url":"https://github.com/johnIT56/CommentSense","commit_stats":null,"previous_names":["johnit56/commentsense"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/johnIT56/CommentSense","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johnIT56%2FCommentSense","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johnIT56%2FCommentSense/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johnIT56%2FCommentSense/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johnIT56%2FCommentSense/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/johnIT56","download_url":"https://codeload.github.com/johnIT56/CommentSense/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/johnIT56%2FCommentSense/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261212459,"owners_count":23125581,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","comment-analysis","content-feedback","gpt-4","llm","nlp","openai","sentiment-analysis","video-insights","youtube"],"created_at":"2025-06-07T11:01:25.016Z","updated_at":"2026-05-07T17:38:52.360Z","avatar_url":"https://github.com/johnIT56.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"#  CommentSense: AI-Powered YouTube Comment Analyzer for Creators 🎥\n\n**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.\n\n\u003e  Designed for creators, brand strategists, and YouTube growth hackers.\n\n![CommentSense Dashboard](screenshots/Dashboard.png)\n\n---\n\n##  Features\n\n- Input any **YouTube video link**\n- Automatically fetches **comments** using the **YouTube Data API**\n- Uses **OpenAI GPT** to analyze:\n  - ✅ Overall audience sentiment\n  - ✅ Strengths of the video\n  - ✅ Weaknesses or pain points\n  - ✅ Suggestions or requests from viewers\n-  Outputs clean, structured insights\n-  Visualized with **Gradio UI**\n\n---\n\n## Use Cases\n\n- **Content Creators** – Understand viewer feedback and plan better content\n- **Marketing Teams** – Gauge brand reception and viewer language\n- **Researchers** – Track sentiment trends and audience behavior\n- **Developers** – Build custom tools around YouTube engagement\n\n---\n\n##  How It Works\n\n1. User enters a YouTube video URL  \n2. Tool extracts the video ID  \n3. Fetches up to 100 top-level comments using the **YouTube Data API v3**  \n4. Sends comment list to **OpenAI GPT-4** with the following prompt:\n\n```python\nsystem_message = \"You are an assistant that analyses YouTube comments\"\nuser_prompt = f\"\"\"Analyse the following comments and tell the channel owner:\n1. Overall audience sentiment\n2. Strengths of the video\n3. Weaknesses\n4. Future content demands or suggestions from viewers.\n\nComments: {comments_list}\n```\n5. Returns a structured analysis for the creator to act on.\n\n![CommentSense Dashboard](screenshots/Analysis.png)\n\n---\n\n## 🛠️ Installation\n\n```bash\ngit clone https://github.com/johnIT56/CommentSense.git\ncd CommentSense\npip install -r requirements.txt\npython app.py\n\n```\n You’ll need a YouTube Data API key and an OpenAI API key set up in your environment or a config file.\n\n---\n\nContributing\nContributions are welcome! Please open issues or pull requests to improve functionality, UI, or model prompts.\n\n---\n\nLicense\nMIT License\n\n---\n\nContact\nBuilt with 💡 by johnIT56\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjohnit56%2Fcommentsense","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjohnit56%2Fcommentsense","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjohnit56%2Fcommentsense/lists"}