User Interaction Dataset for CSCW 2023 paper "How Stated Accuracy of an AI System and Analogies to Explain Accuracy Affect Human Reliance on the System."

DOI:10.4121/f211863d-331b-44e5-a184-c21a18ac831a.v1
The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/f211863d-331b-44e5-a184-c21a18ac831a
Datacite citation style:
He, Gaole; Buijsman, Stefan; Gadiraju, Ujwal (2025): User Interaction Dataset for CSCW 2023 paper "How Stated Accuracy of an AI System and Analogies to Explain Accuracy Affect Human Reliance on the System.". Version 1. 4TU.ResearchData. dataset. https://doi.org/10.4121/f211863d-331b-44e5-a184-c21a18ac831a.v1
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite

Dataset

This repo contains all code, data, and user interfaces associated with the paper "How Stated Accuracy of an AI System and Analogies to Explain Accuracy Affect Human Reliance on the System." It mainly contains a human-AI decision making study within the context of loan approval tasks. We collected user decisions before and after the AI advice with access to stated accuracy of the AI system and analogy to elucidate the stated accuracy. We also provided interface built upon flask to reimplement our experiments.

History

  • 2025-02-06 first online, published, posted

Publisher

4TU.ResearchData

Format

table/csv

Organizations

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Software Technology, Web Information Systems Group

DATA

Files (4)