Predicting YouTube success through facial emotion recognition of video thumbnails

Peter-Duy-Linh Bui, Martin Feldges, Max Liebig and Fabian Weiland

Chapter 7 in Handbook of Social Computing, 2024, pp 142-158 from Edward Elgar Publishing

Abstract: This chapter proposes a correlation analysis and a prediction regarding the success of YouTube video thumbnails based on facial attributes (emotion, ethnicity, age, and gender). For this purpose, all videos created by the 100 most popular German content creators on YouTube are considered. We create a Success Score to measure the success of a YouTube video thumbnail. The Success Score comprises video views, their relative level, and their trend. Using this measurement, the presence of faces within YouTube thumbnails correlates positively with video success. The correlations between video success and facial attributes also differ depending on the video category. In particular, happy faces, for instance, enrich the success of gaming videos, while they reduce success in sports videos. Finally, a classification model is built that can predict YouTube video success using facial attributes from thumbnails.

Keywords: Business and Management; Innovations and Technology; Sociology and Social Policy (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781803921259.00015 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 503 Service Temporarily Unavailable

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:elg:eechap:21469_7

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Darrel McCalla ().