A Multilingual Virtual Guide for Self-Attachment Technique

Abstract

In this work, we propose a computational framework that leverages existing out-of-language data to create a conversational agent for the delivery of Self-Attachment Technique (SAT) in Mandarin. Our framework does not require large-scale human translations, yet it achieves a comparable performance whilst also maintaining safety and reliability. We propose two different methods of augmenting available response data through empathetic rewriting. We evaluate our chatbot against a previous, English-only SAT chatbot through non-clinical human trials (N = 42), each lasting five days, and quantitatively show that we are able to attain a comparable level of performance to the English SAT chatbot. We provide qualitative analysis on the limitations of our study and suggestions with the aim of guiding future improvements.

Proof of Concept for Efficacy of VR-based Self-Attachment Intervention in a Non-Clinical Population

“…Given the low cost of administering VR at scale, compared to in-person psychology services, this may also help improve health accessibility and equity challenges at a global scale. Consistent with these challenging tasks, a chatbot has been developed to coach the user in practising SAT 48 ; and efforts are also made to produce this virtual coach in a multi-language setting 49 .…”