Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Artificial Intelligence Supported Cognitive Behavioral Therapy for Treatment of Speech Anxiety in Virtual Reality Environments
Mid Sweden University, Faculty of Human Sciences, Department of Psychology and Social Work.ORCID iD: 0000-0002-6355-660x
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System Science. (CER)
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and System Science.ORCID iD: 0000-0001-9372-3416
2020 (English)In: Proceedings of the European Conference on the Impact of Artificial Intelligence and Robotics / [ed] Florinda Matos, Reading, UK: Academic Conferences and Publishing International Limited, 2020, Vol. 2Conference paper, Published paper (Refereed)
Abstract [en]

Cognitive behavioral therapy (CBT) has become a successful treatment to improve management of stress and anxiety in social situations. One of the most widespread social anxiety disorders is speech anxiety, and there are also studies reporting that speech anxiety is increasing among younger adults. An emerging trend in CBT treatment is virtual reality (VR), a technology that today also could involve the use of artificial intelligence. The aim of this position paper is to present and discuss the idea of using explainable artificial intelligence to improve CBT treatment of speech anxiety in virtual reality environments.  

The proposed CBT and VR concept builds upon identification of individuals for whom a scientifically grounded treatment can be predicted to have a larger effect than the average. The identification of these individuals should be conducted with the use of Explainable artificial intelligence (XAI). However, the effect of providing XAI-based information on actual treatment outcome has not been fully investigated and established. To better understand how AI-based information can strengthen CBT, it would be valuable to investigate how much confidence individuals undergoing treatment can have in information that is derived from XAI applications. If XAI-derived information is trusted to the same extent as traditional information coming from psychologists, this could open up for CBT design.

Furthermore, the VR-treatment should be grounded in learning theory and cognitive psychology with an emphasis on promotion of inhibitory learning.  A commercial application should be used for stimuli presentation in the VR-head-set based on various scenarios that simulates real-world situations. The main objective of the VR-treatment is to promote inhibitory learning by disproving catastrophic beliefs through exposure to distressful speech situations. Outcomes of the treatment should primarily be measured by the Public Speaking Anxiety Scale, but also involve an assessment of social anxiety with the use of Liebowitz’s Social Anxiety Scale.

Place, publisher, year, edition, pages
Reading, UK: Academic Conferences and Publishing International Limited, 2020. Vol. 2
Keywords [en]
Artificial intelligence, Explainable artificial intelligence, Cognitive behavioral therapy, Virtual reality, Speech anxiety
National Category
Applied Psychology
Identifiers
URN: urn:nbn:se:miun:diva-40284DOI: 10.34190/EAIR.20.030Scopus ID: 2-s2.0-85097823046ISBN: 978-1-912764-74-7 (print)OAI: oai:DiVA.org:miun-40284DiVA, id: diva2:1478637
Conference
ECIAIR 2020
Available from: 2020-10-22 Created: 2020-10-22 Last updated: 2020-12-29Bibliographically approved

Open Access in DiVA

fulltext(880 kB)2323 downloads
File information
File name FULLTEXT01.pdfFile size 880 kBChecksum SHA-512
b005ddda975567cde4d66cfcb7db7a29e3031748f0535b5622324a435a21d17939cadae4e9a6a8322ba96fd6c5c885913ee6b8ce808c103bc446bdfc41ee1ca6
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Åhs, FredrikMozelius, PeterDobslaw, Felix

Search in DiVA

By author/editor
Åhs, FredrikMozelius, PeterDobslaw, Felix
By organisation
Department of Psychology and Social WorkDepartment of Computer and System Science
Applied Psychology

Search outside of DiVA

GoogleGoogle Scholar
Total: 2328 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 2328 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf