Words Worth: Verbal Content and Hirability Impressions in YouTube Video Resumes
Automatic hirability prediction from video resumes is gaining increasing attention in both psychology and computing. Most existing works have investigated hirability from the perspective of nonverbal behavior, with verbal content receiving little interest. In this study, we leverage the advances in deep-learning based text representation techniques (like word embedding) in natural language processing to investigate the relationship between verbal content and perceived hirability ratings. To this end, we use 292 conversational video resumes from YouTube, develop a computational framework to automatically extract various representations of verbal content, and evaluate them in a regression task. We obtain a best performance of R{\mbox{$^2$}} = 0.23 using GloVe, and R{\mbox{$^2$}} = 0.22 using Word2Vec representations for manual and automatically transcribed texts respectively. Our inference results indicate the feasibility of using deep learning based verbal content representation in inferring hirability scores from online conversational video resumes.
PDF Abstract
