TY - CONF T1 - Explaining Sentiment Classification with Synthetic Exemplars and Counter-Exemplars T2 - Discovery Science Y1 - 2020 A1 - Lampridis, Orestis A1 - Riccardo Guidotti A1 - Salvatore Ruggieri ED - Appice, Annalisa ED - Tsoumakas, Grigorios ED - Manolopoulos, Yannis ED - Matwin, Stan AB - We present xspells, a model-agnostic local approach for explaining the decisions of a black box model for sentiment classification of short texts. The explanations provided consist of a set of exemplar sentences and a set of counter-exemplar sentences. The former are examples classified by the black box with the same label as the text to explain. The latter are examples classified with a different label (a form of counter-factuals). Both are close in meaning to the text to explain, and both are meaningful sentences – albeit they are synthetically generated. xspells generates neighbors of the text to explain in a latent space using Variational Autoencoders for encoding text and decoding latent instances. A decision tree is learned from randomly generated neighbors, and used to drive the selection of the exemplars and counter-exemplars. We report experiments on two datasets showing that xspells outperforms the well-known lime method in terms of quality of explanations, fidelity, and usefulness, and that is comparable to it in terms of stability. JF - Discovery Science PB - Springer International Publishing CY - Cham SN - 978-3-030-61527-7 UR - https://link.springer.com/chapter/10.1007/978-3-030-61527-7_24 ER -