Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Likable or Intelligent? Comparing Social Robots and Virtual Agents for Long-term Health Monitoring

Caterina Neef, Anja Richert

TL;DR

The paper addresses how social robots and virtual agents compare as interfaces for long-term health monitoring in older adults in real-world homes. It conducts an eight-week, between-subjects in-home trial where participants choose either a Pepper robot or a Charlotte VA and interact daily with health questionnaires using identical dialog, with GQS captured at baseline and after eight weeks. The findings indicate similar levels of anthropomorphism and animacy between embodiments, but differences in likability (robot) versus perceived intelligence (VA), with a general decline in ratings over time, suggesting a novelty effect. The study highlights design trade-offs between embodied and software-based interfaces and argues for user choice and personalization to sustain engagement, outlining directions for adaptive, personalized SIA and real-world health outcome research.

Abstract

Using social robots and virtual agents (VAs) as interfaces for health monitoring systems for older adults offers the possibility of more engaging interactions that can support long-term health and well-being. While robots are characterized by their physical presence, software-based VAs are more scalable and flexible. Few comparisons of these interfaces exist in the human-robot and human-agent interaction domains, especially in long-term and real-world studies. In this work, we examined impressions of social robots and VAs at the beginning and end of an eight-week study in which older adults interacted with these systems independently in their homes. Using a between-subjects design, participants could choose which interface to evaluate during the study. While participants perceived the social robot as somewhat more likable, the VA was perceived as more intelligent. Our work provides a basis for further studies investigating factors most relevant for engaging interactions with social interfaces for long-term health monitoring.

Likable or Intelligent? Comparing Social Robots and Virtual Agents for Long-term Health Monitoring

TL;DR

The paper addresses how social robots and virtual agents compare as interfaces for long-term health monitoring in older adults in real-world homes. It conducts an eight-week, between-subjects in-home trial where participants choose either a Pepper robot or a Charlotte VA and interact daily with health questionnaires using identical dialog, with GQS captured at baseline and after eight weeks. The findings indicate similar levels of anthropomorphism and animacy between embodiments, but differences in likability (robot) versus perceived intelligence (VA), with a general decline in ratings over time, suggesting a novelty effect. The study highlights design trade-offs between embodied and software-based interfaces and argues for user choice and personalization to sustain engagement, outlining directions for adaptive, personalized SIA and real-world health outcome research.

Abstract

Using social robots and virtual agents (VAs) as interfaces for health monitoring systems for older adults offers the possibility of more engaging interactions that can support long-term health and well-being. While robots are characterized by their physical presence, software-based VAs are more scalable and flexible. Few comparisons of these interfaces exist in the human-robot and human-agent interaction domains, especially in long-term and real-world studies. In this work, we examined impressions of social robots and VAs at the beginning and end of an eight-week study in which older adults interacted with these systems independently in their homes. Using a between-subjects design, participants could choose which interface to evaluate during the study. While participants perceived the social robot as somewhat more likable, the VA was perceived as more intelligent. Our work provides a basis for further studies investigating factors most relevant for engaging interactions with social interfaces for long-term health monitoring.

Paper Structure

This paper contains 5 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Materials and Methods
  4. Results
  5. Discussion and Conclusion

Figures (2)

  • Figure 1: An example is shown of the social robot Pepper and the VA Charlotte asking one of the health-related questions in this study, i.e., "How are you doing today?". Screenshots were translated into English.
  • Figure 2: The GQS scores for the agents Pepper (a) and Charlotte (b) are visualized at the beginning and end of the eight-week study, with minimum values corresponding to 1 and maximum values to 5. All ratings are lower at the end of study, and anthropomorphism and animacy are rated similarly for both agents, while Pepper is perceived as slightly more likable and Charlotte is perceived as more intelligent.