Leveraging Educational Data Mining for Real-time Performance Assessment of Scientific Inquiry Skills within Microworlds

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 1, 2012
Janice D. Gobert Michael A. Sao Pedro Ryan S.J.d. Baker Ermal Toto Orlando Montalvo

Abstract

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.

How to Cite

Gobert, J., Sao Pedro, M., Baker, R., Toto, E., & Montalvo, O. (2012). Leveraging Educational Data Mining for Real-time Performance Assessment of Scientific Inquiry Skills within Microworlds. JEDM | Journal of Educational Data Mining, 4(1), 111-143. Retrieved from https://jedm.educationaldatamining.org/index.php/JEDM/article/view/24
Abstract 429 | PDF Downloads 178

##plugins.themes.bootstrap3.article.details##

Section
Articles