Riccardo Belliato

Artificial Intelligence (AI) literacy is becoming an essential competency across disciplines and stakeholders. However, AI-related education poses important difficulties, as it combines many concerns such as technical skills, ethical/legal issues, critical thinking, etc. These difficulties, combined with the variety of learners background, push towards customizable learning support. Such needs could be better addressed through machine processable representations, as those enable distribution, reuse, and automation mechanisms both from Model-Driven Engineering (MDE) and Generative AI techniques. This paper proposes a framework powered by MDE methodologies to support the conceptualization of the AI literacy domain in terms of competencies and learning scenarios. The conceptualization is realized by means of corresponding metamodels in close collaboration with pedagogy domain experts. The expressiveness of the metamodels is demonstrated in a proof-of-concept developed for AI literacy teaching.

In recent years, environmental sustainability has emerged as a critical issue for society, prompting governments, local authorities, and private organizations to promote initiatives that encourage more sustainable lifestyles. One such initiative is the AWorld application, which leverages gamification to educate, raise awareness, and inspire positive behavioral changes. The app engages users through personalized challenges, or missions, that require interaction with its features and reward participants with in-game points. In this article, we present a hierarchical Multi-Armed Bandit (MAB) framework, MABTree, designed to replace AWorld’s current random mission assignment with a targeted and adaptive approach guided by a custom reward function. Using real-world interaction data from AWorld, we evaluated MABTree in an offline setting across multiple policies and configurations. Results show that MABTree improves cumulative reward, user coverage, and mission diversity compared to classical MAB baselines, with particularly strong gains in balancing exploration of new features and exploitation of known user preferences. While these findings indicate the potential of MABTree to enhance personalization and engagement in sustainability-focused applications, further online testing is needed to validate its real-world impact on long-term user behavior change.