Behind the Screens: Predicting Age Through Social Media Behavior Patterns

Abstract: In the digital era, understanding user behavior on platforms like YouTube can offer insights into demographic patterns such as age. This study explores how YouTube engagement metrics—such as number of comments, subscription duration, and content activity—can be used to predict a user’s age using linear regression. A dataset comprising various user engagement attributes was preprocessed and analyzed. The linear regression model demonstrated that variables like subscription length and profanity index significantly correlate with age, while others had limited predictive value. The study contributes to understanding behavioral patterns of users on social media and showcases the potential of regression-based modeling in social analytics.