摘要：We present Science Assistments, an interactive environment, which assesses students inquiry skills as they engagein inquiry using science microworlds. We frame our variables, tasks, assessments, and methods of analyzing data interms of evidence-centered design. Specifically, we focus on the student model, the task model, and the evidencemodel in the conceptual assessment framework. In order to support both assessment and the provision ofscaffolding, the environment makes inferences about student inquiry skills using models developed through acombination of text replay tagging [cf. Sao Pedro et al. 2011], a method for rapid manual coding of student log files,and educational data mining. Models were developed for multiple inquiry skills, with particular focus on detectingif students are testing their articulated hypotheses, and if they are designing controlled experiments. Student-levelcross-validation was applied to validate that this approach can automatically and accurately identify these inquiryskills for new students. The resulting detectors also can be applied at run-time to drive scaffolding intervention.
