A Multilingual Virtual Guide for Self-Attachment Technique
This work addresses the need for accessible mental health interventions in Mandarin, though it is incremental as it builds on an existing English chatbot.
The authors tackled the problem of delivering Self-Attachment Technique (SAT) in Mandarin without large-scale human translations by proposing a computational framework that uses out-of-language data and empathetic rewriting, achieving comparable performance to an English-only SAT chatbot in non-clinical human trials with 42 participants over five days.
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.