Regresar

Presentation skills estimation based on video and kinect data analysis

Abstract:

This paper identifies, by means of video and Kinect data, a set of pbkp_redictors that estimate the presentation skills of 448 individual students. Two evaluation criteria were pbkp_redicted: eye contact and posture and body language. Machine-learning evaluations resulted in models that pbkp_redicted the perfor- mance level (good or poor) of the presenters with 68% and 63% of correctly classified instances, for eye contact and postures and body language criteria, respectively. Furthermore, the results suggest that certain features, such as arms movement and smoothness, provide high significance on pbkp_redicting the level of development for presentation skills. The paper finishes with conclusions and related ideas for future work.