CoChat
Sign Up
Cited by 35Social Robot Interaction and HRIInnovative Human-Technology InteractionUsability and User Interface Design

“A Second Voice”: Investigating Opportunities and Challenges for Interactive Voice Assistants to Support Home Health Aides

Bartle, Vince, Lyu, Janice, El Shabazz-Thompson, Freesoul, Oh, Yunmin, Chen, Angela Anqi, Chang, Yu-Jan, Holstein, Kenneth, Dell, Nicola·2022·CHI Conference on Human Factors in Computing Systems
DOI 10.1145/3491102.3517683
Open this paper in CoChat — free account

Abstract

Home health aides are a vulnerable group of frontline caregivers who provide personal and medically-oriented care in patients’ homes. Their work is difficult and unpredictable, involving a mix of physical and emotional labor as they adapt to patients’ changing needs. Our paper presents an exploratory, qualitative study with 32 participants, that investigates design opportunities for Interactive Voice Assistants (IVAs) to support aides’ essential care work. We explore challenges and opportunities for IVAs to (1) fill gaps in aides’ access to information and care coordination, (2) assist with decision making and task completion, (3) advocate on behalf of aides, and (4) provide emotional support. We then discuss key implications of our work, including how materiality may impact perceived ownership and usage of IVAs, the need to carefully consider tensions around surveillance, accountability, data collection, and reporting, and the challenges of centering aides as essential workers in complex home health care contexts.

Integrity signals

Registry

Crossref · 10.1145/3491102.3517683

Cites

67 of 67 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Previous HCI research has explored strategies and interactive tools for healthcare communication such as embodied agents, voice assistants, and mobile apps, which do not necessarily involve AI and thus follow more fixed interaction flows.

    “For example, previous HCI research has also explored strategies and interactive tools for healthcare communication such as embodied agents, voice assistants, and mobile apps, which do not necessarily involve AI and thus follow more fixed interaction flows [13,31,32,99,106].”

    From Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults (2024) · cites this paper as [13]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Bartle, V., Lyu, J., El Shabazz-Thompson, F., Oh, Y., Chen, A. A., Chang, Y.-J., Holstein, K., & Dell, N.
Affiliations
  • Jacobs Institute (US)
  • Carnegie Mellon University (US)
  • Human-Computer Interaction Institute, Carnegie Mellon University, United States
ORCID
Venue
CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2022-04-27
Pages
1-17
DOI
10.1145/3491102.3517683
OpenAlex
W4224979805
Cited by
35
References
67
Citations by year
2026: 7 · 2025: 10 · 2024: 7 · 2023: 9 · 2022: 2
FWCI
13.48
Type
conference paper
Language
en
Open access
closed
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
CHI Conference on Human Factors in Computing Systems (publishedVersion)
Funders
National Science Foundation (2026577)
Topics
  • Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
  • Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
  • Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
Keywords
home health aides, care coordination, emotional support, decision support, advocacy, data collection, materiality, essential workers, home health care, caregiver support

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review