DOI QR코드

DOI QR Code

Generative Interactive Psychotherapy Expert (GIPE) Bot

  • Received : 2023.04.05
  • Published : 2023.04.30

Abstract

One of the objectives and aspirations of scientists and engineers ever since the development of computers has been to interact naturally with machines. Hence features of artificial intelligence (AI) like natural language processing and natural language generation were developed. The field of AI that is thought to be expanding the fastest is interactive conversational systems. Numerous businesses have created various Virtual Personal Assistants (VPAs) using these technologies, including Apple's Siri, Amazon's Alexa, and Google Assistant, among others. Even though many chatbots have been introduced through the years to diagnose or treat psychological disorders, we are yet to have a user-friendly chatbot available. A smart generative cognitive behavioral therapy with spoken dialogue systems support was then developed using a model Persona Perception (P2) bot with Generative Pre-trained Transformer-2 (GPT-2). The model was then implemented using modern technologies in VPAs like voice recognition, Natural Language Understanding (NLU), and text-to-speech. This system is a magnificent device to help with voice-based systems because it can have therapeutic discussions with the users utilizing text and vocal interactive user experience.

Keywords

References

  1. Depression [Internet]. World Health Organization. World Health Organization; [cited 2020Dec19]. Available from: https://www.who.int/news-room/factsheets/detail/depression
  2. Covid-19 pandemic triggers 25% increase in prevalence of anxiety and depression worldwide [Internet]. World Health Organization. World Health Organization; [cited 2022Apr6]. Available from: https://www.who.int/news/item/02-03- 2022-covid-19-pandemic-triggers-25-increase-inprevalence-of-anxiety-and-depression-worldwide
  3. Carlo AD, Hosseini Ghomi R, Renn BN, Arean PA. By the numbers: ratings and utilization of behavioral health mobile applications. NPJ digital medicine. 2019 Jun 17;2(1):1-8.  doi: 10.1136/ebmental-2018-300069
  4. Hofmann SG, Asmundson GJ, Beck AT. The science of cognitive therapy. Behavior therapy. 2013 Jun 1;44(2):199-212. doi: 10.1016/j.beth.2009.01.007
  5. Butler AC, Chapman JE, Forman EM, Beck AT. The empirical status of cognitive-behavioral therapy: a review of meta-analyses. Clinical psychology review. 2006 Jan 1;26(1):17-31. doi: 10.1016/j.cpr.2005.07.003
  6. Jurinec N, Schienle A. Utilizing placebos to leverage effects of cognitive-behavioral therapy in patients with depression. Journal of affective disorders. 2020 Dec 1;277:779-84.  doi: 10.1016/j.jad.2020.08.087
  7. Kepuska V, Bohouta G. Improving wake-up-word and general speech recognition systems. In2017 IEEE 15th Intl Conf on Dependable, Autonomic and Secure Computing, 15th Intl Conf on Pervasive Intelligence and Computing, 3rd Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress  (DASC/PiCom/DataCom/CyberSciTech) 2017 Nov 6 (pp. 318-321). IEEE. doi: 10.1109/DASC-PIComDataCom-CyberSciTec.2017.67
  8. Khalaf AA, Hashim AH, Olowolayemo A, Funke R. Artificial Intelligent Applications for Mental Health Support: A Review paper. Engineering Professional Ethics and Education 2021 (ICEPEE'21). 2021 Jun 22:22.
  9. Varghese E, Pillai MR. A standalone generative conversational interface using deep learning. In2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT) 2018 Apr 20 (pp. 1915-1920). IEEE. doi: 10.1109/ICICCT.2018.8473211
  10. CounselChat. Mental health answers from counselors [Internet]. CounselChat. [cited 2020Dec]. Available from: https://counselchat.com/
  11. Bertagnolli N, Lord G, Strom E, Lee P. Counsel chat: Bootstrapping high-quality therapy data [Internet]. 2020 [cited 2020Dec]. Available from: https://towardsdatascience.com/counsel-chat-bootstrappinghigh-quality-therapy-data-971b419f33da
  12. Serban I, Sordoni A, Lowe R, Charlin L, Pineau J, Courville A, Bengio Y. A hierarchical latent variable encoder-decoder model for generating dialogues. InProceedings of the AAAI Conference on Artificial Intelligence 2017 Feb 12 (Vol. 31, No. 1). doi: 10.1609/aaai.v31i1.10983
  13. Serban I, Klinger T, Tesauro G, Talamadupula K, Zhou B, Bengio Y, Courville A. Multiresolution recurrent neural networks: An application to dialogue response generation. InProceedings of the AAAI Conference on Artificial Intelligence 2017 Feb 12 (Vol. 31, No. 1). doi: 10.1609/aaai.v31i1.10984
  14. Li, J., Monroe, W., Ritter, A., Galley, M., Gao, J., & Jurafsky, D. (2016-a). Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541. doi: 10.48550/arXiv.1606.01541
  15. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.