Please use this identifier to cite or link to this item: https://dl.eusset.eu/handle/20.500.12015/4162
Title: Towards “Explorable” AI: Learning from ML Developers’ Sensemaking Practices
Authors: Wolf, Christine T.
Issue Date: 2021
Publisher: European Society for Socially Embedded Technologies (EUSSET)
metadata.dc.relation.ispartof: Proceedings of 19th European Conference on Computer-Supported Cooperative Work
Series/Report no.: ECSCW
ECSCW
Abstract: In this note, we report on a qualitative design study in the field of machine learning (ML) and in particular on the sensemaking practices of ML developers as they interact with the interface of a novel adversarial AI method. This paper makes contributions to discourses on interpretable or explainable AI (XAI) systems through an empirical understanding of ML developers’ sensemaking practices. These findings make salient the concept of “explorability” as an alternative design metaphor for interactive AI systems – instead of a focus on explainability or interpretability as fixed qualities of AI systems, explorability focuses on emergent meanings and ways in which they might be enabled or constrained through practice.
metadata.dc.identifier.doi: 10.18420/ecscw2021_n28
URI: https://dl.eusset.eu/handle/20.500.12015/4162
ISSN: 2510-2591
metadata.mci.conference.sessiontitle: Notes
metadata.mci.conference.location: Zurich, Switzerland
metadata.mci.conference.date: 7-11 June 2021
Appears in Collections:ECSCW 2021 Exploratory Papers and Notes

Files in This Item:
File SizeFormat 
ecscw2021-n28.pdf831,58 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.