Enhancing Conversations in Migrant Counseling Services: Designing for Trustworthy Human-AI Collaboration
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
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
2024-05-20
Department
Major/Subject
Human-Computer Interaction and Design
Mcode
SCI3020
Degree programme
Master's Programme in ICT Innovation
Language
en
Pages
57+13
Series
Abstract
Migrants arriving or residing in Finland require a variety of counseling and support services, in municipal contexts such as the City of Espoo, to successfully integrate into Finnish society. This thesis conducts qualitative and user experience research using a series of participatory design methods to understand the challenges migrants face on arrival and then explores novel, theory-driven design concepts for improving communication between these users and municipal service advisors. The three main objectives of this thesis are: 1) understanding the challenges faced by service advisors and their customers in the context of migration to Finland, 2) designing and prototyping improved user experience concepts using participatory research methods, and 3) evaluating a proof-of-concept design approach in an appropriate use case scenario. The key findings are twofold. First, our empirical findings suggest that migrant customers often lack knowledge of how municipal services are organized and service advisors guide them in navigating complex information across different digital services. Second, our design concept highlights the importance of supporting the relevant intentions and expectations when evaluating the adequacy of AI-generated visual summaries that can enhance conversations between service advisors and migrant customers. The goals of the design research is not to replace service advisors, but to enhance their ability to better support migrant customers in real-time interactions. Finally, we offer theoretical implications. By reifying a conversation into a manipulable object, we can augment knowledge sharing. This digital ``boundary object" can act as a memory aid when reused by customers and service advisors at a later date. Future research should focus on how AI-augmented service counseling can affect trust in computer-supported collaborative settings.Description
Supervisor
Mackay, WendyThesis advisor
Wollstén, PiiaSawhney, Nitin
Keywords
human-AI interaction, conversational user interfaces, service design, trust, migration