Commen'Sense

Machine learning Project based on sentiment comment analysis

Introduction

This is a machine learning project for sentiment analysis of YouTube video comments. The project uses Google's API to fetch comments from a particular video and then analyzes the sentiment of each comment using a logistic regression model trained on 1.6 million tweets. The project also provides a graphical user interface (GUI) to make it easy for users to input the video link and view the analysis results.

Real Life Use- Case

• For users: The project provides an easy and convenient way to analyze the sentiment of comments on YouTube videos. This can help users get a better understanding of the overall sentiment of a video's comments, which can be useful in determining whether a video is worth watching or not. Additionally, the treeview of all the comments can provide a quick overview of what people are saying about a particular video.

• For YouTubers: By analyzing the sentiment of their video comments, YouTubers can gain valuable insights into how their content is being received by their audience. This information can help them identify areas where they can improve their content and engage with their audience more effectively. Additionally, by understanding the overall sentiment of their comments, YouTubers can make data-driven decisions about their content strategy and see how their efforts are impacting their audience.

GUI

Project Details

The project has the following components:

• Google API: The Google API is used to fetch comments from a particular YouTube video. The API returns a list of comments and other metadata associated with the video.

• TKinter GUI: The project uses the TKinter library to create a graphical user interface that allows users to input the YouTube video link and view the analysis results. The GUI displays the percentage of positive and negative comments, as well as a treeview of all the comments.

• Logistic Regression Model: The project uses a logistic regression model to classify the sentiment of each comment as positive or negative. The model was trained on 1.6 million tweets and has an accuracy of over 80%.

Usage

To use this project, you need to have the following software installed on your machine:

• Python 3.x
• TKinter library
• Google API client library

Conclusion

This project demonstrates how machine learning can be used to analyze the sentiment of YouTube video comments. By using the Google API to fetch comments and the logistic regression model to classify the sentiment, this project provides a simple and effective way to gain insights into the sentiment of online comments. The TKinter GUI makes it easy for users to input the video link and view the analysis results, making this project accessible and user-friendly.

Overall, this project can be a valuable tool for both users and YouTubers, helping them make informed decisions and engage with their audience in a more meaningful way.