Springe direkt zu Inhalt

Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability

Benjamin, Jesse Josua; Kinkeldey, Christoph; Müller-Birn, Claudia; Korjakow, Tim; Herbst, Eva-Maria – 2022

During a research project in which we developed a machine learning (ML) driven visualization system for non-ML experts, we reflected on interpretability research in ML, computer-supported collaborative work and human-computer interaction. We found that while there are manifold technical approaches, these often focus on ML experts and are evaluated in decontextualized empirical studies. We hypothesized that participatory design research may support the understanding of stakeholders' situated sense-making in our project, yet, found guidance regarding ML interpretability inexhaustive. Building on philosophy of technology, we formulated explanation strategies as an empirical-analytical lens explicating how technical explanations mediate the contextual preferences concerning people's interpretations. In this paper, we contribute a report of our proof-of-concept use of explanation strategies to analyze a co-design workshop with non-ML experts, methodological implications for participatory design research, design implications for explanations for non-ML experts and suggest further investigation of technological mediation theories in the ML interpretability space.

Title
Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability
Author
Benjamin, Jesse Josua; Kinkeldey, Christoph; Müller-Birn, Claudia; Korjakow, Tim; Herbst, Eva-Maria
Publisher
ACM
Location
New York
Date
2022
Identifier
10.1145/3492858
Source(s)
Appeared in
Proceedings of the ACM on Human-Computer Interaction 6
Language
eng
Type
Text
BibTeX Code
@article{10.1145/3492858,
author = {Benjamin, Jesse Josua and Kinkeldey, Christoph and M\"{u}ller-Birn, Claudia and Korjakow, Tim and Herbst, Eva-Maria},
title = {Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability},
year = {2022},
issue_date = {January 2022},
publisher = {ACM},
address = {New York, NY, USA},
volume = {6},
number = {GROUP},
url = {https://doi.org/10.1145/3492858},
doi = {10.1145/3492858},
journal = {Proc. ACM Hum.-Comput. Interact.},
month = {jan},
articleno = {39},
numpages = {25},
keywords = {post-phenomenology, explanation strategies, explainable machine learning, subject-matter experts, participatory design}
}