User engagement and sentiment analysis on YouTube food videos

Abstract

This dissertation was written as a part of the Master in Information Systems at the University of Macedonia. YouTube has become one of the most popular social media platforms in recent years. The purpose of this study is to investigate the sentiment behind user engagement and content consumption on YouTube. In this study we investigate the effects of engagement volume and diversity, demonstrating experimentally that these are two crucial components of engagement behavior that together influence its efficacy. The study seeks to explore the associations between user engagement metrics and sentiment in food-related YouTube video channels from extracted datasets. This research focuses on the use of social media data mining tools to identify relevant information in massive datasets. The results detected negative associations between the metric of likes and the emotion of anger in most channels, while positive associations were detected between the number of comments and the sentiments of anger and surprise. Despite the fact that video content related to food on the investigated YouTube channels is similar, the commenters on all channels exhibit very few commonalities.