London Metropolitan University & Brunel University London
Communication Skills Training Intervention Based on Automated Recognition of Nonverbal Signals
There have been promising studies that show a potential of providing social signal feedback to improve communication skills. However, these studies have primarily focused on unimodal methods of feedback. In addition to this, studies do not assess whether skills are maintained after a given time. With a sample size of 22 this paper investigates whether multimodal social signal feedback is an efective method of improving communication in the context of media interviews. A pre-post experimental evaluation of media skills training intervention is presented which compares standard feedback with augmented feedback based on automated recognition of multimodal social signals. Results revealed signifcantly different training efects between the two conditions. However, the initial experiment study failed to show signifcant diferences in human judgement of performance. A 6-month follow-up study revealed human judgement ratings were higher for the experiment group. This study suggests that augmented selective multimodal social signal feedback is an effective method for communication skills training.
Capturing facial expressions and hand movements were synchronized on iMotions which is a Biometric Research Platform. Facial expressions were detected using AFFDEX by Afectiva a Facial Action Coding Unit System (FACS) which detects Action Units (AU) which are derived from facial muscles, associated with basic emotions
Social Signals, Communication skills training, Media interviews, Of-the-shelf emotion recognition technology