EXPLORING THE RELATIONSHIP BETWEEN BODY EXPRESSIONS AND ELECTRODERMAL ACTIVITY IN PUBLIC SPEAKING ANXIETY.

Abstract

Over the last decade, a significant amount of research has been dedicated to understanding public speaking anxiety (PSA) and building systems for practicing public speaking skills. Input to these systems is often multimodal, focusing on verbal and nonverbal communication, including conversational gestures, vocal characteristics, gaze behavior, and physiological responses (such as electrodermal activity (EDA)). However, it is unclear how, when and why some behaviors manifest. That is, if we can determine potential behaviors that contribute to elevating or easing the speakerÕs anxiety level, this information can be integrated into an interactive virtual audience within a training platform for public speaking and passed on to the speaker as individualized feedback. Reflecting on this feedback may help those suffering from PSA learn to better mitigate their PSA by gaining insight and awareness into their PSA-related expressions as a step toward learning how to employ potential coping strategies. Inspired by Lee & KleinsmithÕs previous work, the goal of this thesis is to explore features (expression and EDA) that relate to perceived PSA and how information from these modalities can be implemented into the design of a public speaking training platform. We applied ordinal logistic regression to measure the contribution of each feature in predicting audience-perceived PSA of the speakers after which we applied unsupervised K-means clustering to explore how students were grouped according to body and EDA features only. The results of each model are compared and contrasted, leading to a set of guidelines for designing a public speaking training platform.