Laurence Capus

Although VEs, including eTandems, have become increasingly widespread within second and FL teaching, such is not the case in Canada, especially in school contexts. To explore the viability of eTandem exchanges within this context, action research projects were set up in French-language elementary and secondary schools in the province of Quebec, where students were learning English or Spanish. Partners were recruited within English language schools within Canada or internationally (in Australia, the United States, or Mexico). Data were collected using questionnaires, interviews, and students’ texts. This chapter reports on the potential benefits of eTandem exchanges for students as well as the challenges faced by teachers in regard to their implementation. The complexity of innovation in this context is further discussed in relation to Activity Theory.

This article provides an in-depth review of the concepts of interpretability and explainability in machine learning, which are two essential pillars for developing transparent, responsible, and trustworthy artificial intelligence (AI) systems. As algorithms become increasingly complex and are deployed in sensitive domains, the need for interpretability has grown. However, the ongoing confusion between interpretability and explainability has hindered the adoption of clear methodological frameworks. To address this conceptual ambiguity, we draw on the formal distinction introduced by Dib, which rigorously separates interpretability from explainability. Based on this foundation, we propose a revised classification of explanatory approaches structured around three complementary axes: intrinsic vs. extrinsic, specific vs. agnostic, and local vs. global. Unlike many existing typologies that are limited to a single dichotomy, our framework provides a unified perspective that facilitates the understanding, comparison, and selection of methods according to their application context. We illustrate these elements through an experiment on the Breast Cancer dataset, where several models are analyzed: some through their intrinsically interpretable characteristics (logistic regression, decision tree) and others using post hoc explainability techniques such as treeinterpreter for random forests. Additionally, the LIME method is applied even to interpretable models to assess the relevance and robustness of the locally generated explanations. This contribution aims to structure the field of explainable AI (XAI) more rigorously, supporting a reasoned, contextualized, and operational use of explanatory methods.