Megha, FNU (2019-08). MITIGATING PUBLIC SPEAKING ANXIETY USING VIRTUAL REALITY AND POPULATION-SPECIFIC MODELS. Master's Thesis. Thesis uri icon

abstract

  • In the education and workplace landscape of the 21st century, it is often said that a person is only as valuable as the ideas s/he has and can share. Public speaking skills are essential to help people effectively exchange ideas, persuade, inform their audiences as well as make a tangible impact. They also plays a vital role in one's academic and professional success. However, research shows that public speaking anxiety (PSA) ranks as a top social phobia among many people and tends to be aggravated in minorities, first generation students, and non-native speakers. This research aims at mitigating this anxiety by utilizing physiological (cardiovascular activity, electrodermal activity etc.) and acoustic (pitch, intonation, etc.) indices captured from wearable devices and virtual reality (VR) interfaces to quantify and predict PSA. This work also examines the significance of individual-specific factors, such as general trait anxiety and personality metrics, as well as contextual factors, such as age, gender, highest education, and native language, receny of public speaking in moderating the association between bio-behavioural (physiological and acoustic) indices and PSA. The individual-specific information is used to develop population-specific machine learning models of PSA. Results of this research highlight the importance of including such factors for detecting PSA with the proposed population-based PSA models yielding Spearman's correlation of 0.55 n(p < 0.05) between the actual and predicted state-based scores. This work further analyzes whether systematic exposure to public speaking tasks in a VR environment can help alleviate PSA. Results indicate that systematic exposure to public speaking in VR can alleviate PSA in terms of both self-reported (p < 0.05) and physiological (p < 0.05) indices. Findings of this study will enable researchers to better understand antedecedents and causes of PSA as well as lay the foundation toward developing adaptive behavioural interventions for social communication disorders using systematic exposure (e.g., through VR stimuli), relaxation feedback, and cognitive restructuring.
  • In the education and workplace landscape of the 21st century, it is often said that a person is only as valuable as the ideas s/he has and can share. Public speaking skills are essential to help people effectively exchange ideas, persuade, inform their audiences as well as make a tangible impact. They also plays a vital role in one's academic and professional success. However, research shows that public speaking anxiety (PSA) ranks as a top social phobia among many people and tends to be aggravated in minorities, first generation students, and non-native speakers. This research aims at mitigating this anxiety by utilizing physiological (cardiovascular activity, electrodermal activity etc.) and acoustic (pitch, intonation, etc.) indices captured from wearable devices and virtual reality (VR) interfaces to quantify and predict PSA. This work also examines the significance of individual-specific factors, such as general trait anxiety and personality metrics, as well as contextual factors, such as age, gender, highest education, and native language, receny of public speaking in moderating the association between bio-behavioural (physiological and acoustic) indices and PSA.
    The individual-specific information is used to develop population-specific machine learning models of PSA. Results of this research highlight the importance of including such factors for detecting PSA with the proposed population-based PSA models yielding Spearman's correlation of 0.55 n(p < 0.05) between the actual and predicted state-based scores. This work further analyzes whether systematic exposure to public speaking tasks in a VR environment can help alleviate PSA. Results indicate that systematic exposure to public speaking in VR can alleviate PSA in terms of both self-reported (p < 0.05) and physiological (p < 0.05) indices. Findings of this study will enable researchers to better understand antedecedents and causes of PSA as well as lay the foundation toward developing adaptive behavioural interventions for social communication disorders using systematic exposure (e.g., through VR stimuli), relaxation feedback, and cognitive restructuring.

publication date

  • August 2019