Large repositories of presentation recordings (e.g.,“Videolectures” and “Academic Earth”) often provide their userswith rating facilities. The rating of a presentation certainlydepends on the content, but the way the content is delivered islikely to play a role as well. This paper focuses on the latter aspectand shows that nonverbal behavior (in particular arms movementand prosody) allows one to predict whether a presentation is ratedas low or high in terms of quality. The experiments have beenperformed over 100 presentations collected from “Videolectures”and the accuracy is up to 66% depending on the techniquesadopted. In other words, nonverbal communication actuallyinfluences the ratings assigned to a presentation.
Learning How to Teach from "Videolectures": Automatic Prediction of Lecture Ratings Based on Teacher's Nonverbal Behavior
CRISTANI, Marco;MURINO, Vittorio
2012-01-01
Abstract
Large repositories of presentation recordings (e.g.,“Videolectures” and “Academic Earth”) often provide their userswith rating facilities. The rating of a presentation certainlydepends on the content, but the way the content is delivered islikely to play a role as well. This paper focuses on the latter aspectand shows that nonverbal behavior (in particular arms movementand prosody) allows one to predict whether a presentation is ratedas low or high in terms of quality. The experiments have beenperformed over 100 presentations collected from “Videolectures”and the accuracy is up to 66% depending on the techniquesadopted. In other words, nonverbal communication actuallyinfluences the ratings assigned to a presentation.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.