"I don't know how to help with that" - Learning from Limitations of Modern Conversational Agent Systems in Caregiving Networks-Reference-Cited by-同舟云学术

"I don't know how to help with that" - Learning from Limitations of Modern Conversational Agent Systems in Caregiving Networks

Published:2023-09-28 Issue:CSCW2 Volume:7 Page:1-28
ISSN:2573-0142
Container-title:Proceedings of the ACM on Human-Computer Interaction
language:en
Short-container-title:Proc. ACM Hum.-Comput. Interact.

Author:

Zubatiy Tamara¹^ORCID,Mathur Niharika¹^ORCID,Heck Larry¹^ORCID,Vickers Kayci L.²^ORCID,Rozga Agata¹^ORCID,Mynatt Elizabeth D.³^ORCID

Affiliation:

1. Georgia Institute of Technology, Atlanta, GA, USA

2. Emory University, Atlanta, GA, USA

3. Northeastern University, Boston, MA, USA

Abstract

While commercial conversational agents (CA) (i.e. Google assistant, Siri, Alexa) are widely used, these systems have limitations in error-handling, flexibility, personalization and overall dialogue management that are amplified in care coordination settings. In this paper, we synthesize and articulate these limitations through quantitative and qualitative analysis of 56 older adults interacting with a commercial CA deployed in their home for a 10 week period. We look at the CA as a compensatory technology in an older adult's care network. We argue that the CA limitations are rooted in the rigid cue-and-response style of task-oriented interactions common in CAs. We then propose a redesign for CA conversation flow to favor flexibility and personalization that is nonetheless viable within the limitations of current AI and machine learning technologies. We explore design tradeoffs to better support the usability needs of older adults compared to current design optimizations driven by efficiency and privacy goals.

Funder

National Science Foundation

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Human-Computer Interaction,Social Sciences (miscellaneous)

Link

https://dl.acm.org/doi/pdf/10.1145/3610170

Reference48 articles.

1. Daniel Adiwardana Minh-Thang Luong David R So Jamie Hall Noah Fiedel Romal Thoppilan Zi Yang Apoorv Kulshreshtha Gaurav Nemade Lu etal 2020. Towards a human-like open-domain chatbot. ArXiv:2001.09977 (2020). Daniel Adiwardana Minh-Thang Luong David R So Jamie Hall Noah Fiedel Romal Thoppilan Zi Yang Apoorv Kulshreshtha Gaurav Nemade Lu et al. 2020. Towards a human-like open-domain chatbot. ArXiv:2001.09977 (2020).

2. Working together to learn new oral hygiene techniques: Pilot of a carepartner-assisted intervention for persons with cognitive impairment

3. A home-based individualized information communication technology training program for older adults: a demonstration of effectiveness and value;Arthanat Sajay;Disability and Rehabilitation: Assistive Technology,2016

4. Multi-stakeholder perspectives on information communication technology training for older adults: implications for teaching and learning

5. Renato FL Azevedo , Dan Morrow , James Graumlich , Ann Willemsen-Dunlap , Mark Hasegawa-Johnson , Thomas S Huang , Kuangxiao Gu , Suma Bhat , Tarek Sakakini , Victor Sadauskas , 2018 . Using conversational agents to explain medication instructions to older adults. In AMIA annual symp . proceedings , Vol. 2018 . American Medical Informatics Association, 185. Renato FL Azevedo, Dan Morrow, James Graumlich, Ann Willemsen-Dunlap, Mark Hasegawa-Johnson, Thomas S Huang, Kuangxiao Gu, Suma Bhat, Tarek Sakakini, Victor Sadauskas, et al. 2018. Using conversational agents to explain medication instructions to older adults. In AMIA annual symp. proceedings, Vol. 2018. American Medical Informatics Association, 185.