A1 Refereed original research article in a scientific journal
AI representing personas representing user groups: Applying the agency theory to examine interaction challenges of conversational personas as decision-making tools
Authors: Salminen, Joni; Jung, Soon-Gyo; Kaate, Ilkka; Xuan, Trang Thi Thu; Azem, Jinan Y.; Aldous, Kholoud Khalil; Amin, Danial; Jansen, Bernard J.
Publisher: Elsevier BV
Publication year: 2026
Journal: Decision Support Systems
Article number: 114633
Volume: 205
ISSN: 0167-9236
eISSN: 1873-5797
DOI: https://doi.org/10.1016/j.dss.2026.114633
Publication's open availability at the time of reporting: Open Access
Publication channel's open availability : Partially Open Access publication channel
Web address : https://doi.org/10.1016/j.dss.2026.114633
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/523238440
Self-archived copy's licence: CC BY
Self-archived copy's version: Publisher`s PDF
The proliferation of artificial intelligence (AI) technologies has led to the rise of conversational decision-making support systems, such as dialogue persona systems that provide conversational access to various user segments. For example, product managers can ask personas about features before implementing them, politicians can learn about the needs of local communities through personas, and so on. Nascent research has looked at challenges when users interact with AI personas, but has not framed it as a principal–agent problem, in which the AI represents a persona that itself represents real people in the data. This setting exposes unique interaction challenges that decision makers face when engaging with AI-generated conversational personas, which we examine through a user study with 56 participants using AI-generated conversational personas. Our results indicate seven interaction challenges: (1) Hidden Information, (2) Hidden Personas, (3) Hidden UI, (4) Lack of AI Agency, (5) AI’s Selective Attention, (6) Confusing Distributional Information, and (7) Conversational Cold Start that we conceptually link with agency theory. We discuss how the interaction challenges could be alleviated and suggest directions for future work.
Downloadable publication This is an electronic reprint of the original article. |  |
