Madeleine Steeds

Madeleine Steeds

Auto-generated profile, based on publicly available information

Madeleine Steeds

Smurfit Business School, University College Dublin, Dublin, Ireland

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 April 2020
Verified
Conference Paper
Open access
CSCorina Sas
Corina Sas
NDNigel Davies
Nigel Davies
SCSarah Clinch
Sarah Clinch
PSPeter Shaw
Peter Shaw
MMMateusz Mikusz
Mateusz Mikusz
LNLukas Nohrer
Lukas Nohrer
Beside reminiscing, the increasing cognitive decline in dementia can also be addressed through sensory stimulation allowing the immediate, nonverbal engagement with the world through one's senses. Much HCI work has prioritized cognitive stimulation for reminiscing or personhood often on small screens, while less research has explored sensory stimulation like the one enabled by large displays. We describe a year-long deployment in a residential care home of a wall-sized display, and explored its domestication through 24 contextual interviews. Findings indicate strong engagement and attachment to the display which has inspired four psychosocial interventions using online generic content. We discuss the value of these findings for personhood through residents' exercise of choices, the tension between generic/personal content and its public/private use, the importance of participatory research approach to domestication, and the infrastructure-based prototype, illustrated by the DementiaWall and its generative quality.

4 November 2024 in International Journal of Human-Computer Studies
Verified
Journal Article
Closed access
IGIona Gessinger
Iona Gessinger
KSKatie Seaborn
Katie Seaborn
MSMadeleine Steeds
Madeleine Steeds
BCBenjamin R. Cowan
Benjamin R. Cowan

11 May 2024
Verified
Conference Paper
Open access
TFTakao Fujii
Takao Fujii
KSKatie Seaborn
Katie Seaborn
MSMadeleine Steeds
Madeleine Steeds
ChatGPT is a conversational agent built on a large language model. Trained on a significant portion of human output, ChatGPT can mimic people to a degree. As such, we need to consider what social identities ChatGPT simulates (or can be designed to simulate). In this study, we explored the case of identity simulation through Japanese first-person pronouns, which are tightly connected to social identities in intersectional ways, i.e., intersectional pronouns. We conducted a controlled online experiment where people from two regions in Japan (Kanto and Kinki) witnessed interactions with ChatGPT using ten sets of first-person pronouns. We discovered that pronouns alone can evoke perceptions of social identities in ChatGPT at the intersections of gender, age, region, and formality, with caveats. This work highlights the importance of pronoun use for social identity simulation, provides a language-based methodology for culturally-sensitive persona development, and advances the potential of intersectional identities in intelligent agents.


1 August 2021 in Computers in Human Behavior Reports
Verified
Journal Article
Open access
MSMadeleine Steeds
Madeleine Steeds
SCSarah Clinch
Sarah Clinch
CJCaroline Jay
Caroline Jay

25 April 2025
Verified
Conference Paper
Open access
MOMolly O'REilly-Kime
Molly O'REilly-Kime
YFYifan Feng
Yifan Feng
FCFrancesca Cipelli
Francesca Cipelli
EOEkat Osipova
Ekat Osipova
KKKay Kender
Kay Kender
JRJennifer Rode
Jennifer Rode