BookTubing Across Regions: Examining Differences Based on Nonverbal and Verbal Cues

Abstract

BookTubers are a rapidly growing community in YouTube who shares content related to books. Previous literature has addressed problems related to automatically analyzing opinions and mood of video logs (vlogs) as a generic category in YouTube. Unfortunately, the population studied is not diverse. In this work, we study and compare some aspects of the geographic/cultural context of BookTube videos, comparing non-western (Indian) and Western populations. The role played by nonverbal and verbal cues in each of these contexts are analyzed automatically using audio, visual, and text features. The analysis shows that cultural context and popularity can be inferred to some degree using multimodal fusion of these features. The best obtained results are an average precision-recall score of 0.98 with Random Forest in a binary India vs. Western video classification task, and 0.75 in inferring binary popularity levels of BookTube videos. CCS CONCEPTS • Human-centered computing → Social media; • Social and professional topics → Cultural characteristics; • Computing methodologies → Supervised learning by classification.

Becoming a Good BookTuber

“…As Sorensen and Mara (2014) claim, giving students an opportunity to provide feedback on the work of their peers is essential as knowledge is constructed from participation in the community created for activities in informal learning contexts. Based on previous analyses of similar audiovisual productions and multimodal productions of expert BookTubers, this feedback served to foster the students’ multimodal communicative competence (López, 2016; Sued, 2017; Thomas et al, 2019).…”