It is challenging to make informational videos interesting and engaging. Our project aims to perform a case study on one of the most successful informational YouTube channels with over 202,000 videos called TEDx. The goal is to figure out the characteristics that make TEDx so successful so that other informational content creators can apply the same techniques.
The case study will aim to perform EDA on various engagement statistics like views, likes, comments, duration, tags, etc. Also, determine the top-performing videos and what makes them popular. Utilize Topic modeling ML models to identify prevalent themes or topics across TEDx videos.
Descriptive Statistics : Analysis of Engagement statisticsÂ
Performance and Engagement Metrics : Compare views, likes, and comments with categories, video duration, and tags.
Content Analysis : Use topic modeling and keyword extraction to identify themes.
Trend Analysis : Analyze trends in viewership and engagement over time.
Tools:
Use h2o predict function to compare the model’s predicted values with absolute values.
Use h20 auc to determine the accuracy of the best model.
Based on the predictions we will identify the categories which are more popular.