Virtual Voices, Real Insights: Sentiment and Topic Analysis of Discussions about Educational Dropout in YouTube comments

Abstract

The present study addresses the prevalent issue of high dropout rates in post-secondary education. It aims to expand understanding of the reasons for dropping out from both higher education (HE) and vocational education and training (VET) while also exploring the utilization of social media data as an approach for empirical educational research. Leveraging text mining approaches, such as topic modeling and sentiment analysis, the study analyzes comments from YouTube videos addressing dropout in HE and VET contexts. The research questions focus on the suitability of these methods for gaining insights into dropout phenomena, identifying relevant topics associated with dropout in both educational sectors, and the sentiments expressed towards dropout. Results suggest that comments on VET dropout videos often center around financial and working condition issues, while those on HE dropout videos are generally optimistic and future-focused. Overall, sentiments are primarily neutral to positive, with HE dropout comments being more positive than those on VET dropout.