Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Categorizing Sources of Information for Explanations in Conversational AI Systems for Older Adults Aging in Place

Niharika Mathur, Tamara Zubatiy, Elizabeth Mynatt

TL;DR

The paper addresses the challenge of generating context-aware explanations in conversational AI for older adults aging in place, arguing that multi-user home environments require explanations drawn from diverse information sources. It proposes an initial framework that categorizes home information into four main categories—User Historical Data, Salient Environment Data, Task Data, and AI System Data—to tailor explanations and support cross-technology collaboration. The approach is grounded in longitudinal studies with older adults with MCI and caregivers, offering a practical taxonomy and design guidance along with discussion of challenges like implicit feedback capture and privacy. This work advances user-centric, context-aware CAI design for aging-in-place scenarios and lays the groundwork for evaluating how different explanation sources affect user trust and confidence.

Abstract

As the permeability of AI systems in interpersonal domains like the home expands, their technical capabilities of generating explanations are required to be aligned with user expectations for transparency and reasoning. This paper presents insights from our ongoing work in understanding the effectiveness of explanations in Conversational AI systems for older adults aging in place and their family caregivers. We argue that in collaborative and multi-user environments like the home, AI systems will make recommendations based on a host of information sources to generate explanations. These sources may be more or less salient based on user mental models of the system and the specific task. We highlight the need for cross technological collaboration between AI systems and other available sources of information in the home to generate multiple explanations for a single user query. Through example scenarios in a caregiving home setting, this paper provides an initial framework for categorizing these sources and informing a potential design space for AI explanations surrounding everyday tasks in the home.

Categorizing Sources of Information for Explanations in Conversational AI Systems for Older Adults Aging in Place

TL;DR

The paper addresses the challenge of generating context-aware explanations in conversational AI for older adults aging in place, arguing that multi-user home environments require explanations drawn from diverse information sources. It proposes an initial framework that categorizes home information into four main categories—User Historical Data, Salient Environment Data, Task Data, and AI System Data—to tailor explanations and support cross-technology collaboration. The approach is grounded in longitudinal studies with older adults with MCI and caregivers, offering a practical taxonomy and design guidance along with discussion of challenges like implicit feedback capture and privacy. This work advances user-centric, context-aware CAI design for aging-in-place scenarios and lays the groundwork for evaluating how different explanation sources affect user trust and confidence.

Abstract

As the permeability of AI systems in interpersonal domains like the home expands, their technical capabilities of generating explanations are required to be aligned with user expectations for transparency and reasoning. This paper presents insights from our ongoing work in understanding the effectiveness of explanations in Conversational AI systems for older adults aging in place and their family caregivers. We argue that in collaborative and multi-user environments like the home, AI systems will make recommendations based on a host of information sources to generate explanations. These sources may be more or less salient based on user mental models of the system and the specific task. We highlight the need for cross technological collaboration between AI systems and other available sources of information in the home to generate multiple explanations for a single user query. Through example scenarios in a caregiving home setting, this paper provides an initial framework for categorizing these sources and informing a potential design space for AI explanations surrounding everyday tasks in the home.
Paper Structure (11 sections, 1 figure)

This paper contains 11 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Contribution
  3. Method
  4. Framing the Context
  5. The Initial Framework
  6. Category 1 - User Historical Data
  7. Category 2 - Salient Environment Data
  8. Category 3 - Task Data
  9. Category 4 - AI System Data
  10. Challenges and Technical Opportunities
  11. Conclusion and Future Work

Figures (1)

  • Figure 1: This initial framework categorizes sources of information in the home into 4 larger categories with 9 subcategories.