Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Christian Poglitsch, Johanna Pirker

TL;DR

The paper addresses social communication challenges in Autism Spectrum Disorder and proposes empathetic conversational agents as gamified training partners. It uses a qualitative design, conducting seven expert interviews to elicit requirements for agent characteristics, visualization, interaction, and evaluation, informed by existing literature on virtual agents and LLMs. The study identifies two feasible agent roles—conversation partner and training partner—and highlights design considerations such as multimodal communication, progression via adaptive quests, and diverse visualization styles. The work provides design guidance for developing ASD-focused social skills tools that leverage generative agents and gamification to support real-life skill transfer.

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.

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

TL;DR

The paper addresses social communication challenges in Autism Spectrum Disorder and proposes empathetic conversational agents as gamified training partners. It uses a qualitative design, conducting seven expert interviews to elicit requirements for agent characteristics, visualization, interaction, and evaluation, informed by existing literature on virtual agents and LLMs. The study identifies two feasible agent roles—conversation partner and training partner—and highlights design considerations such as multimodal communication, progression via adaptive quests, and diverse visualization styles. The work provides design guidance for developing ASD-focused social skills tools that leverage generative agents and gamification to support real-life skill transfer.

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.
Paper Structure (15 sections, 1 figure)

This paper contains 15 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Develop questionnaire
  5. Recruit Experts
  6. Data Analysis
  7. Results
  8. Background of recruited experts
  9. Design Aspects
  10. Communication
  11. Visualization
  12. Feedback and adaptation
  13. Evaluation
  14. Summary
  15. Discussion

Figures (1)

  • Figure 1: Proposed framework for initiating conversations with an agent, incorporating a starting quest.