How adaptive social robots influence cognitive, emotional, and self-regulated learning

Abstract

Abstract As educational environments become more diverse, adaptive technologies like social robots hold promise for providing individual support to learners. This study investigated the role of adaptive teaching of a robot on students’ learning outcomes, emotions, and self-regulated learning (SRL). A total of 120 participants (aged 18–60 years, M age = 30.25, SD age = 10.06, 64.3% female) engaged in an interactive vocabulary learning task with varying guidance levels by the robot. Control conditions included fixed guidance, offering either simple guidance with no hints (condition 1) or enhanced guidance, constantly adding hints (condition 2). In the adaptive conditions, the robot adjusted the number of hints based on learners’ recent performance and enjoyment (condition 3) or additionally personalized hints to specific mistakes (condition 4). The results showed no direct or indirect effects of adaptive guidance on task performance or cognitive learning compared to fixed guidance. Instead, adaptive guidance significantly reduced on-task enjoyment compared to enhanced guidance, suggesting that unexpected variability in robot behavior may negatively affect emotional learning experience. However, personalized adaptive guidance increased certain SRL behaviors, indirectly benefiting learning outcomes. These findings highlight the need for further refinement of adaptive social robots to better meet individual learner needs and optimize outcomes.