Manuscript received March 29, 2022, revised April 15, 2022; revised June 12, 2022.
Abstract—The project aims to boost the mental health of Australians using RASA-trained chatbots. JoyBot was trained with a hugging-face classifier, developed with RASA (Receive, Appreciate, Summarize, Ask), Docker and deployed with Stream-Lit. The EDA results showed that long-term health condition, Family type, Job status, House loans types and location of Australians had a significant effect on Australians’ psychological distress level during and after the COVID lockdown, the hugging face transformer classified with Sentiment_VADER, 96% negative and 4% positive with candidate_labels: “Panic”, “Anger”, “Sad”, “Happy”, “Brave”. We deployed Joybot with Streamlit and tested it with Intent Prediction Confidence Distribution showed that chatbot conversation was predicted correctly with 1. JoyBot would serve as a helping hand for Australians, guide them through Frequent Answering Questions (FAQ) and a directory for every Psychologist, thereby reducing the overall workload on the Mental health sector in Australia.
Index Terms—COVID-19, mental health, Australians, RASA, Sentiment_VADER, Streamlit
Mary Adewunmi is with SPIS, NACETEM, Lagos, Nigeria and Department of Medical Studies, University of Tasmania (UTAS), Hobart, Australia (e-mail: mary@moaanalytic.com).
Adish Ashraff is with Aigility, Australia (e-mail: adish.ashraff@gmail.com).
Tanya Dixit is with Australian National University(ANU), Australia (e-mail: Tanya.Dixit@anu.edu.au).
Nikhil Shrestha is with HDFC Bank, India (e-mail: n.shrestha17@gmail.com).
Veronica Gail Medrano is with Cascadeo Corporation, Phillipines (e-mail: nicamedrano98@gmail.com).
Ahmed Fahim is with University of Dhaka, Dhaka, Bangladesh (e-mail: afahim03@yahoo.com).
Navaneeth Tirupath is with OMDENA-Australia chapter, Australia (e-mail: navant@gmail.com).
Sudha Sushma is with Maharaja Surajmal Institute of Technology, New Delhi, India (e-mail: sushma.nippani2000@gmail.com).
*Correspondence: buchougule@outlook.com (B.C.)
Cite: Mary Adewunmi, Adish Ashraff, Tanya Dixit, Nikhil Shrestha, Veronica Gail Medrano, Bhushan Chougule*, Ahmed Fahim, Navaneeth Tirupath, and Sudha Sushma, "JoyBot: RASA-Trained Chatbots to Provide Mental Health Assistance for Australians," International Journal of Machine Learning vol. 13, no. 3, pp. 109-116, 2023.
Copyright @ 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).