Analyzing the temporal evolution of students' behaviors in open-ended learning environments

Metacognition and self-regulation are important for developing effective learning in the classroom and beyond, but novice learners often lack effective metacognitive and self-regulatory skills. However, researchers have demonstrated that metacognitive processes can be developed through practice and appropriate scaffolding. Betty's Brain, an open-ended computer-based learning environment, helps students practice their cognitive skills and develop related metacognitive strategies as they learn science topics. In this paper, we analyze students' activity sequences in a study that compared different categories of adaptive scaffolding in Betty's Brain. The analysis techniques for measuring students' cognitive and metacognitive processes extend our previous work on using sequence mining methods to discover students' frequently-used behavior patterns by (i) developing a systematic approach for interpreting derived behavior patterns using a cognitive/metacognitive task model and (ii) analyzing the evolution of students' frequent behavior patterns over time. Our results show that it is possible to identify students' learning behaviors and analyze their evolution as they work in the Betty's Brain environment. Further, the results illustrate that changes in student behavior were generally consistent with the scaffolding provided, suggesting that these metacognitive strategies can be taught to middle school students in computer-based learning environments.