Predicting online lecture ratings based on gesturing and vocal behavior

• Published in: Journal on multimodal user interfaces Vol. 8; no. 2; pp. 151 - 160
• Main Authors: Cheng, Dong Seon, Salamin, Hugues, Salvagnini, Pietro, Cristani, Marco, Vinciarelli, Alessandro, Murino, Vittorio
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-06-2014
• Subjects: Computer Science; Image Processing and Computer Vision; Original Paper; Signal,Image and Speech Processing; User Interfaces and Human Computer Interaction; Video lectures; Generative modeling; Social signal processing; Classification
• ISSN: 1783-7677; 1783-8738
• DOI: 10.1007/s12193-013-0142-z

Nonverbal behavior plays an important role in any human–human interaction. Teaching—an inherently social activity—is not an exception. So far, the effect of nonverbal behavioral cues accompanying lecture delivery was investigated in the case of traditional
ex-cathedra
lectures, where students and teachers are co-located. However, it is becoming increasingly more frequent to watch lectures online and, in this new type of setting, it is still unclear what the effect of nonverbal communication is. This article tries to address the problem and proposes experiments performed over the lectures of a popular web repository (“Videolectures”). The results show that automatically extracted nonverbal behavioral cues (prosody, voice quality and gesturing activity) predict the ratings that “Videolectures” users assign to the presentations.