Analyzing Adaptive Scaffolds that Help Students Develop Self-Regulated Learning Behaviors
share
Providing adaptive scaffolds to help learners develop self-regulated learning (SRL) processes has been an important goal for intelligent learning environments. In this paper, we develop a systematic framework for adaptive scaffolding in Betty's Brain, an open-ended learning-by-teaching environment that helps middle school students learn science by constructing a causal model to teach a virtual agent, generically named Betty. Given the open ended nature of the environment, novice learners often face difficulties in their learning and teaching tasks. We detect key cognitive-metacognitive inflection points, i.e., instances where students' behaviors and performance change as they work on their learning and teaching tasks. At such inflection points, Mr. Davis (a mentor agent) or Betty (the teachable agent) provide conversational feedback, focused on strategies to help students become productive learners. We analyze data collected from a classroom study with 98 middle school students to analyze the impact of the scaffolds on students' learning performance and behaviors. We discuss how our findings will support the next iteration of our adaptive scaffolding framework to help students develop their SRL behaviors when working in OELEs.
READ FULL TEXT