Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability
This work addresses the problem of making ML interpretability more accessible and contextually relevant for non-ML experts, though it is incremental by building on existing theories in philosophy of technology.
The paper tackled the gap in machine learning interpretability research, which often focuses on ML experts and decontextualized studies, by developing explanation strategies as a lens to analyze how technical explanations mediate interpretations for non-ML experts, resulting in insights from a co-design workshop and implications for participatory design and explanation design.
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.