Adaptive feedback from artificial neural networks facilitates pre-service teachers’ diagnostic reasoning in simulation-based learning

A meta-analysis (435 studies, k = 994, N > 61,000) of empirical research on the effects of feedback on student learning was conducted with the purpose of replicating and expanding the Visible Learning research (Hattie and Timperley, 2007; Hattie, 2009; Hattie and Zierer, 2019) from meta-synthesis. Overall results based on a random-effects model indicate a medium effect (d = 0.48) of feedback on student learning, but the significant heterogeneity in the data shows that feedback cannot be understood as a single consistent form of treatment. A moderator analysis revealed that the impact is substantially influenced by the information content conveyed. Furthermore, feedback has higher impact on cognitive and motor skills outcomes than on motivational and behavioral outcomes. We discuss these findings in the light of the assumptions made in The power of feedback (Hattie and Timperley, 2007). In general, the results suggest that feedback has rightly become a focus of teaching research and practice. However, they also point toward the necessity of interpreting different forms of feedback as independent measures. Show more