Towards real interpretability of student success prediction combining methods of XAI and social science

Cohausz, Lea

PDF
2022.EDM-short-papers.33.pdf - Veröffentlichte Version
Download (245kB)

URN:	urn:nbn:de:bsz:180-madoc-624824
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2022
Buchtitel:	Proceedings of the 15th International Conference on Educational Data Mining
Seitenbereich:	361-367
Veranstaltungstitel:	EDM 2022 : The 15th International Conference on Educational Data Mining
Veranstaltungsort:	Durham, UK
Veranstaltungsdatum:	24.-27.07.2022
Herausgeber:	Mitrovic, Antonija ; Bosch, Nigel ; Cristea, Alexandra I. ; Brown, Chris
Ort der Veröffentlichung:	Durham
Verlag:	International Educational Data Mining Society
Verwandte URLs:	https://educationaldatamining.org/edm202...
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
Bereits vorhandene Lizenz:	Creative Commons Namensnennung, nicht kommerziell, keine Bearbeitung 4.0 International (CC BY-NC-ND 4.0)
Fachgebiet:	004 Informatik
Abstract:	Despite calls to increase the focus on explainability and interpretability in EDM and, in particular, student success prediction, so that it becomes useful for personalized intervention systems, only few efforts have been undertaken in that direction so far. In this paper, we argue that this is mainly due to the limitations of current Explainable Artificial Intelligence (XAI) approaches regarding interpretability. We further argue that the issue, thus, calls for a a combination of AI and social science methods utilizing the strengths of both. For this, we introduce a step-wise model of interpretability where the first step constitutes of knowing important features, the second step of understanding counterfactuals regarding a particular person’s prediction, and the third step of uncovering causal relations relevant for a set of similar students. We show that LIME, a current XAI method, reaches the first but not subsequent steps. To reach step two, we propose an extension to LIME, Minimal Counterfactual-LIME, finding the smallest number of changes necessary to change a prediction. Reaching step three, however, is more involved and additionally requires theoretical and causal reasoning - to this end, we construct an easily applicable framework. Using artificial data, we showcase that our methods can recover connections among features; additionally, we demonstrate its applicability on real-life data. Limitations of our methods are discussed and collaborations with social scientists encouraged.