Youtube Comment Sentiment Analysis

This repository contains Jupyter notebooks for building a sentiment analysis data pipeline focused on YouTube video comments. The project uses Natural Language Processing (NLP) techniques to extract, clean, and analyze text data, generating actionable insights and recommending educational content.

Project Overview

Key Features

• Data Extraction and Cleaning: A pipeline for fetching and preprocessing YouTube comments, ensuring the data is clean and structured for analysis.
• Sentiment Analysis: Utilizes NLP techniques to classify comments based on sentiment (e.g., positive, neutral, negative).
• Insights Generation: Derives insights from sentiment trends and provides recommendations for educational content.

Notebooks

1. Extract&Clean-YouTube-Comments.ipynb

   • Handles the extraction of YouTube comments and their preprocessing.
   • Includes steps to clean and structure the data.

2. Sentiment_YouTube.ipynb

   • Implements the sentiment analysis pipeline.
   • Applies machine learning and statistical models to classify sentiment.

3. TextBlob.ipynb

   • Demonstrates the use of the TextBlob library for sentiment analysis.
   • Includes examples of text tokenization, polarity, and subjectivity analysis.

Tools and Libraries

• Programming Language: Python
• Libraries:
  • Pandas: For data manipulation and cleaning.
  • NumPy: For numerical operations.
  • Matplotlib: For data visualization.
  • TextBlob: For sentiment analysis and NLP tasks.

How to Use

1. Clone this repository:

   git clone https://github.com/your-repo-url.git

. Run the notebooks in the following order:

• Extract&Clean-YouTube-Comments.ipynb
• Sentiment_YouTube.ipynb
• TextBlob.ipynb

3. Explore the results and insights generated by the sentiment analysis pipeline.

Results

• The sentiment analysis model achieved an accuracy of 89.67%, demonstrating its effectiveness in classifying YouTube comments.
• Visualizations and insights provide actionable recommendations for curating educational content.