A Qualitative Investigation to Design Empathetic Agents as Conversation Partners for People with Autism Spectrum Disorder

TL;DR

This paper explores designing empathetic AI conversation partners for people with Autism Spectrum Disorder, aiming to improve social skills through gamified interactions and expert insights.

Contribution

It introduces a framework for developing empathetic conversational agents tailored for ASD social skill training based on expert interviews.

Findings

Identified two use cases: conversation and training partners.

Proposed gamified interaction with quests and rewards.

Initial insights into requirements for empathetic agents in ASD support.

Abstract

Autism Spectrum Disorder (ASD) can profoundly affect reciprocal social communication, resulting in substantial and challenging impairments. One aspect is that for people with ASD conversations in everyday life are challenging due to difficulties in understanding social cues, interpreting emotions, and maintaining social verbal exchanges. To address these challenges and enhance social skills, we propose the development of a learning game centered around social interaction and conversation, featuring Artificial Intelligence agents. Our initial step involves seven expert interviews to gain insight into the requirements for empathetic and conversational agents in the field of improving social skills for people with ASD in a gamified environment. We have identified two distinct use cases: (1) Conversation partners to discuss real-life issues and (2) Training partners to experience various scenarios to improve social skills. In the latter case, users will receive quests for interacting with the agent. Additionally, the agent can assign quests to the user, prompting specific conversations in real life and providing rewards for successful completion of quests.