Dive into the world of YouTube data analysis as Presenter W.W.C.M. Waidyarathna explores the popularity levels of video categories based on metadata attributes. Discover how this research can help advertisement industries find suitable video categories for targeted countries and times. Explore the challenges, goals, methodology, and potential applications of this intriguing study.
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
YouTube Data Analysis Presenter : W.W.C.M. Waidyarathna (2015/CSC/012) Supervisor : Dr. S. Mahesan
Introduction My research is about analyzing YouTube videos metadata to arrange YouTube video categories according to their popularity level in ascending or descending order for particular country in different time range.
Goals To find the ranks of YouTube video categories in a particular region in a particular time range. By finding the most popular video category in a country, we can get and idea about how minds of the people of that country work.
Challenges To find the popularity distribution of YouTube video categories, we need to consider about metadata like views, likes, dislikes, shares and is it a trending video or not. So we need to find a relation among those attributes. Finding the popularity level of each video category by using above relationship .
Application Commercial advertisement industries can find the top ranks of video categories which are suitable for the background of the advertisement in particular countries in that time. As an example, suppose sports is the most popular video category in a particular country. So advertisement companies can make advertisements with sport backgrounds for that country.
Methodology Design a program to access YouTube videos metadata using YouTube data API. Find the relationship among metadata attribute using machine learning. Based on that relationship calculate new position value for each video categories. Based on that value we can find popularity distribution for video categories.
Related Works Trending Videos: Measurement and Analysis -Takes 4000 trending videos on YouTube and calculate the probability of a trending video to become popular.
REFERENCES Iman Barjasteh , H. Radha , and Y. Liu , Trending Videos: Measurement and Analysis , Michigan State University , 16 January 2015. K. Filippova, and K. B. Hall, Improved video categorization from text metadata and user comments , SIGIR New York, pp. 835-842, 2011.
