Abstract
Social Signal Processing techniques have given the opportunity to analyze in-depth human behavior in social face-to-face interactions. With recent advancements, it is henceforth possible to use these techniques to augment social interactions, especially human behavior in oral presentations. The goal of this study is to train a computational model able to provide a relevant feedback to a public speaker concerning his/her coverbal communication. Hence, the role of this model is to augment the social intelligence of the orator and then the relevance of his/her presentation. To this end, we present an original interaction setting in which the speaker is equipped with only wearable devices. Several coverbal modalities have been extracted and automatically annotated namely speech volume, intonation, speech rate, eye gaze, hand gestures, and body movements. In this article, which is an extension of our previous article published in IUI'17, we compare our Dynamic Bayesian Network design to classical J48/Multi-Layer Perceptron/Support Vector Machine classifiers, propose a subjective evaluation of presenter skills with a discussion in regards to our automatic evaluation, and we add a complementary study about using DBScan versus k-means algorithm in the design process of our Dynamic Bayesian Network.