Designing an emotionally intelligent conversational system to support home-based reminiscence therapy for older adults

Thumbnail Image

Files

master_Zhuo_Yanzhu_2025.pdf (12.35 MB)

URL

Journal Title

Journal ISSN

Volume Title

School of Science | Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.

Authors

Date

2025-07-22

Department

Major/Subject

Human-Computer Interaction and Design

Mcode

Degree programme

Master's Programme in ICT Innovation

Language

en

Pages

66

Series

Abstract

This thesis studies the impact of designing an emotionally intelligent home-based reminiscence therapy (RT) system on older adults’ user engagement and experience when interacting with an AI conversational assistant, as well as its effects on supporting caregivers in RT collaboration. The motivation comes from the increasing psychological and emotional challenges faced by the aging population. While RT is a well-established psychosocial intervention to enhance emotional well-being and identity continuity, its application at home without professional facilitation remains limited by the lack of emotional guidance and tools for monitoring emotional responses. The research follows a user-centered design (UCD) framework. Secondary research was conducted during the context of use analysis to explore the challenges of home-based RT and to identify the needs of older adults and caregivers. The study then proceeded with persona development, task analysis, iterative prototyping, and remote usability testing involving older adult-caregiver pairs. The main results and findings indicate that the designed high-fidelity prototype, which combines a web-based voice user interface with real-time emotion detection and a caregiver dashboard for emotional insights, was well accepted by users. Older adults described the system as intuitive and emotionally supportive, while caregivers appreciated the emotional summaries for monitoring well-being and tailoring future sessions. The evaluation also revealed improvement opportunities, including enhancing content personalization, clarifying emotional scoring, and refining speech interaction cues. This thesis contributes practical design insights for developing empathetic, transparent, and accessible digital mental health tools. The findings demonstrate the potential of emotion-aware voice-based systems to complement human care and facilitate meaningful emotional experiences for older adults in home settings.

Description

Supervisor

Nieminen, Mika P.

Thesis advisor

Villalba Mora, Elena

Keywords

reminiscence therapy, voice user interface, emotional intelligence, ageing-in place, user-centered design, empathic design

Other note

Citation

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202508196348

Collections

[dipl] Perustieteiden korkeakoulu / SCI