Publication
Machine Learning and Knowledge Discovery in Databases
Alexander Wilhelm; Katharina Anna Zweig
In: Machine Learning and Knowledge Discovery in Databases. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), September 9-13, Springer Nature, 2024.
Abstract
In this article, we introduce a socioinformatic method to identify interesting research questions around xAI approaches. Socioinformatics is the field of analyzing effects of software on individuals, groups, and society at large. This field focuses on those actions a software facilitates and those it complicates. Together with all affected groups of actors and their main motivation, the software creates a socioinformatic system. We then look at so-called qualitative effect networks that describe a simple type of interaction between the actors' motivations and so-called system variables that describe the state of the system in a meaningful way. Based on this qualitative effect network, we then try to identify important system dynamics. In this paper, we will introduce this method at the specific example of the societal goals when using xAI approaches and show how this kind of analysis can help to identify relevant causal structures inside a given socioinformatic system, while also illuminating new and important research questions.