🤖🔍 How Do We Really Use AI Chat vs. Traditional Web Search?
Check out "Blending Queries and Conversations" by Kerstin Mayerhofer, Rob Capra, and David Elsweiler to get answers to this question.
🧩 The study explores how people interact with a hybrid Web Search + GenAI Chat interface for health information tasks, providing insights into trust, verification, and system choice in search and chat interactions.
Key insights are:
✔️ Trust and confidence drive tool choice
✔️ Chat feels easy—but often leads to increased confidence despite incorrect results
✔️ 78 search tactics uncovered across both tools
🔗📄 Read the paper here: dl.acm.org/doi/full/10.1145/3698204.3716454
💡🛠️ A worthwhile read for anyone designing or studying human-AI interaction!
The paper was presented at #CHIIR25 and is based on the Master's thesis of our talented former student Kerstin Mayerhofer supervised by our David Elsweiler in overseas collaboration with the one and only Rob Capra (UNC School of Information and Library Science).
#AIChat #GenAI #TrustInAI
#WebSearch
#SystemChoice
#HumanCenteredAI
#HCI #InformationRetrieval
#Research #EmpiricalStudy #MixedMethods
#ResearchSuccess #ResearchPaperAccepted
#CHIIR2025
#UNCSchoolOfInformationAndLibraryScience
#InformationScienceRegensburg #StayInformed
Informationen/Kontakt
Kerstin Mayerhofer hat 2024 ihre Masterarbeit unter Betreuung von PD Dr. David Elsweiler und Prof. Dr. Robert Capra (University of North Carolina at Chapel Hill) am Lehrstuhl für Informationswissenschaft verfasst.
PD Dr. David Elsweiler ist akademischer Oberrat und Dozent am Lehrstuhl für Informationswissenschaft. Weitere Informationen zu David Elsweiler (einschließlich weiterer Forschungsarbeiten) findest Du auf der Webseite von David Elsweiler. – David.Elsweiler(at)ur.de (öffnet Ihr E-Mail-Programm)
Literaturverweis
Kerstin Mayerhofer, Rob Capra, and David Elsweiler. 2025. Blending Queries and Conversations: Understanding Trust, Verification, and System Choice in Search and Chat Interactions. In Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR '25). Association for Computing Machinery, New York, NY, USA, 168–178. https://doi.org/10.1145/3698204.3716454 (externer Link, öffnet neues Fenster)
