https://github.com/ginga1402/youtube_engagement_system

Exploratory Data Analysis on YouTube Data & Likes Prediction
https://github.com/ginga1402/youtube_engagement_system

data-science exploratory-data-analysis linear-regression random-forest-regression

Last synced: about 1 month ago
JSON representation

Exploratory Data Analysis on YouTube Data & Likes Prediction

• Host: GitHub
• URL: https://github.com/ginga1402/youtube_engagement_system
• Owner: Ginga1402
• License: mit
• Created: 2023-06-13T17:04:09.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2024-02-11T19:33:31.000Z (11 months ago)
• Last Synced: 2024-02-11T21:03:59.315Z (11 months ago)
• Topics: data-science, exploratory-data-analysis, linear-regression, random-forest-regression
• Language: Jupyter Notebook
• Homepage:
• Size: 109 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# YouTube_Engagement_System

## Introduction:

The YouTube Engagement System is a project aimed at analyzing and predicting the engagement levels of YouTube videos. It leverages machine learning techniques and data analysis to gain insights into factors that influence video engagement and provides a framework for predicting the engagement of new videos.

In today's digital landscape, YouTube has become a powerful platform for content creators and businesses to reach their target audience. Understanding the factors that drive engagement, such as likes, views, comments, and shares, is crucial for optimizing video content and maximizing its impact.

The YouTube Engagement System project offers a comprehensive solution for analyzing video engagement data, identifying patterns, and predicting future engagement levels. By utilizing this system, content creators and businesses can make informed decisions to enhance their video strategies, increase viewer engagement, and achieve their goals.



## Project Overview :

The Youtube Engagement System project leverages Python libraries and machine learning algorithms to perform the following tasks:

1) Analyze views data from youtube to gain insights into various aspects of the business.

2) Perform exploratory data analysis (EDA) to understand the dataset and identify patterns, trends, and outliers.

3) Visualize the data using charts and graphs to provide meaningful representations of the vital information.

4) Train a machine learning model to predict future Likes based on historical data.

5) Evaluate the model's performance and make predictions on new, unseen data.

## Libraries Used:

1) pandas

2) numpy 

3) matplotlib 

4) seaborn 

5) scikit-learn

6) Squarify

7) Google.Colab

## Data Description :

### Dataset Link :

https://drive.google.com/drive/folders/1jzV_EDI7LppZoFwVzA6HqBUL-p8_mUAw?usp=sharing

The dataset for the YouTube Engagement System project should contain the following columns:

video_id: Unique identifier for each video.

title: Title of the video.

publishedAt: Date and time of video publication.

channelId: Unique identifier for the channel associated with the video.

channelTitle: Title of the channel associated with the video.

categoryId: Identifier for the category to which the video belongs.

trending_date: Date when the video started trending.

tags: Tags associated with the video.

view_count: Number of views the video has received.

likes: Number of likes the video has received.

dislikes: Number of dislikes the video has received.

comment_count: Number of comments the video has received.

thumbnail_link: URL link to the video thumbnail.

comments_disabled: Indicator of whether comments are disabled for the video (True/False).

ratings_disabled: Indicator of whether ratings are disabled for the video (True/False).

description: Description of the video.

## Conclusion

The YouTube Engagement System project provides a valuable toolkit for analyzing and predicting engagement levels for YouTube videos. By leveraging machine learning techniques and data analysis, content creators and businesses can gain insights into the factors influencing engagement and make data-driven decisions to optimize their video strategies.

Start using the YouTube Engagement System today to unlock the power of data and enhance your YouTube video engagement.