Skip to content

using large language models (LLMs) such as Ollama or Gemini to perform transcript summarization into topics and sentiment analysis of comments, all while handling YouTube data extraction.

Notifications You must be signed in to change notification settings

dinirichard/YT-Transcript-and-Comment-Sentiments

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

yt_comments_sentiments

To install dependencies:

bun install

To run:

bun run ./src/main.ts

This project was created using bun init in bun v1.2.2. Bun is a fast all-in-one JavaScript runtime.

Get a youtube video and extract the transcript and comments. Summarize the transcript into topics using LLM(Gemini). Get the sentiments of the comments based on the topics using an LLM( Gemini).

High-Level Flow Diagram;

                    +------------------------+
                    | YouTube Video URL |
                    +------------------------+
                                |
                                v
                    +------------------------+ (API Request)
                    | Backend API Layer |
                    +------------------------+
                                |
                                v
                    +------------------------+
                    | Data Extraction | <-- (Transcript & Comments)
                    +------------------------+
                                |
                                v
                    +------------------------+
                    | Data Preprocessing | <-- (Clean and Normalize)
                    +------------------------+
                                |
                                v
                    +------------------------------------------+
                    | LLM Processing Module |
                    | ------------------------------ |
                    | 1. Transcript Summarization (Topics) |
                    | 2. Comment Sentiment Analysis (by Topic) |
                    +------------------------------------------+
                                |
                                v
                    +------------------------+
                    | Persistence & Caching |
                    +------------------------+
                                |
                                v
                    +------------------------+
                    | Visualization/UI |
                    +------------------------+

About

using large language models (LLMs) such as Ollama or Gemini to perform transcript summarization into topics and sentiment analysis of comments, all while handling YouTube data extraction.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published