%0 Computer Program %A Liscio, Enrico %A Araque, Oscar %A Gatti, Lorenzo %A Constantinescu, Ionut %A Jonker, C.M. (Catholijn) %A Kalimeri, Kyriaki %A Murukannaiah, Pradeep K. %D 2023 %T What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric - code %U %R 10.4121/1e71138c-be26-4652-971a-48a84837df8e.v1 %K NLP %K Morality %K Ethics %K XAI %K natural language processing %K explainable artificial intelligence %X

Code for the paper "What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric", published at ACL '23. This code implements Tomea, an Explainable AI method for investigating the difference in how language models represent morality across domains. Given a pair of datasets and models trained on the datasets, Tomea generates 10 m-distances and one d-distance to measure the difference between the datasets, based on the SHAP method. We make pairwise comparisons of seven models trained on the MFTC datasets (available at this DOI: 10.4121/646b20e3-e24f-452d-938a-bcb6ce30913c).

%I 4TU.ResearchData