Adaptive Contextual Task Engine (ACTE): A Mastery-Aware Task Recommender for Mobile Language Learning in Real-World Contexts

This dataset contains anonymized results from a pilot feasibility study (N=10) evaluating the Adaptive Contextual Task Engine (ACTE) algorithm—a mastery-aware, location-based task recommender for mobile language learning. The study was conducted in a simulated café environment with university students (aged 18–23) practicing A2-level English speaking tasks. Data includes demographics, System Usability Scale (SUS) responses, task relevance ratings, and open-ended feedback. The ACTE algorithm is designed to support "Contextual Immersion Learning," where language practice is triggered by real-world semantic contexts (e.g., cafés, hospitals) and structured around CEFR-aligned modules, badge-based mastery, and time-sensitive performance scoring.