Youtube Trending Video Metadata Analysis Using Machine Learning

Abstract

Data Analysis and Mining are becoming indispensable part of every major organization to
find recent trends and statistics and formulate business strategies, planning and marketing.
However, most of the Data generated is generally in Huge Size and comes in unstructured
format. Big Data cannot be analyzed by traditional database systems and processes. To resolve
this issue, many new tools that implement Parallel Processing are being deployed in these
organizations. As part of the Advanced Databases Project, we propose to perform Data Analysis
of YouTube data. We extracted data of 5 Million Video records from YouTube API and
performed Data Analysis on the data to insight into latest trends and user engagement in
YouTube with respect to Categories and Year. Data Analysis and Visualization was done using
Anaconda jupyter Notebook. Analysis of structured data has seen tremendous success in the past.
However, analysis of large scale unstructured data in the form of video format remains a
challenging area. YouTube, a Google company, has over a billion users and generates billions of
views. Since YouTube data is getting created in a very huge amount and with an equally great
speed, there is a huge demand to store, process and carefully study this large amount of data to
make it usable.