Relational Agents for the Homeless with Tuberculosis Experience: Providing Social Support Through Human-agent Relationships

Yi Hyun Jang, Soo Han Im, Younah Kang, Joon Sang Baek

Research output: Contribution to journalArticlepeer-review


In human-computer interaction (HCI) research, relational agents (RAs) are increasingly used to improve social support for vulnerable groups including people exposed to stigmas, alienation, and isolation. However, technical support for tuberculosis (TB) patients, one such vulnerable group, remains insufficient due to the nature of the infectious disease and difficulties in accessing the homeless community. To derive design considerations for developing RAs targeting homeless TB patients, we conducted an empirical study on the patients. Data were collected through participatory observations and interviews and were processed using deductive thematic analysis. The patients' environmental and behavioral characteristics were classified, which showed that understanding these factors in the design of an RA is important because the patients' perception, attitudes, and expectations towards the agent are shaped by (and also shape) their environmental and behavioral characteristics, which consequently affect the nature of relationships formed between them. Therefore, we drew the following design considerations: (1) protection of privacy is a prerequisite to the use of an RA for homeless TB patients and can be addressed from both short-term (technical) and long-term (sociotechnical) perspectives; (2) the homeless group emphasized affective support from the agent, suggesting that relationships per se are already valuable to people who have been socially isolated and stigmatized; (3) consideration of the past memories in selecting social cues can facilitate the exchange of affective expressions in user-agent interaction; and (4) an RA should clarify to its interlocuters its identity as a machine to avoid confusing people with low technological literacy.

Original languageEnglish
Article number15
JournalACM Transactions on Interactive Intelligent Systems
Issue number2
Publication statusPublished - 2022 Jun

Bibliographical note

Funding Information:
The reviewing of this article was managed by special issue associate editors Baki Kocaballi, Liliana Laranjo, Leigh Clark, Robert J. Moore, Rafal Kocielnik, Q. Vera Liao, and Timothy W. Bickmore. This study was funded by the Ministry of Science and ICT of the Republic of Korea and the National Information Society Agency. We are grateful to the interview participants for their valuable contributions. Authors’ address: Y. H. Jang, S. H. Im, Y. Kang, and J. S. Baek, Yonsei University, 50, Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea (03722); emails:,,, Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from © 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM. 2160-6455/2022/07-ART15 $15.00

Publisher Copyright:
© 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM.

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Artificial Intelligence


Dive into the research topics of 'Relational Agents for the Homeless with Tuberculosis Experience: Providing Social Support Through Human-agent Relationships'. Together they form a unique fingerprint.

Cite this