Impact of Artificial Intelligence-enabled Automated Adaptive Feedback on Students’ Motivational and Cognitive Learning Outcomes in Scenario-based Learning

Research Objective(s): 1. To examine the different specific features of adaptive feedback. 2. To investigate the effects of adaptive and static feedback on students’ motivational and cognitive learning outcomes. Artificial intelligence (AI) development makes the automation of adaptive feedback feasible and efficient. However, studies about automated adaptive feedback on student motivation are scant. These relevant questions are unanswered. What are the different specific features of adaptive feedback? What elements should the feedback adapt to for enhanced learning (Bernacki et al., 2021)? How does adaptive feedback affect learners’ motivation and cognitive learning performance? This study aims to address these important questions. In this research, we apply automatic adaptive feedback in chatbot format in an SBL setting. The primary aim of this research is to examine the effects of automated adaptive feedback on student intrinsic motivation in scenario-based learning compared with static feedback. This work may help explore how adaptive feedback may affect students’ different aspects of motivation (i.e., affective, behavioural and cognitive). Second, we will provide easy-to-follow guidance for teachers on using AI to automate adaptative feedback and design SBL tasks for improved student motivation.

Funding Source: RGC - Germany/HK Joint Research Scheme