Paper Summary
Share...

Direct link:

Introduction to Computational Cognitive Modeling and Educational Assessment

Sat, April 18, 2:15 to 3:45pm, Virtual Room

Abstract

The purpose of this presentation is to describe the work that will be covered in the introductory chapters of the proposed book. This section involves reviewing current work in the areas of computational cognitive modeling (CCM) and assessment, focusing on the types of models that have been proposed and evaluated in the literature.
Thinking about readers with an educational assessment background, we will introduce CCM and its relevance to assessment, review the history of CCM, and describe different CCM frameworks, such as information processing approaches and cognitive architectures (e.g., ACT-R (Anderson, 2007); PRIMs (Taatgen, 2013)). Then, focusing on readers with a cognitive science background, we will provide general information about assessment, including types of assessments (e.g., formative and summative), basic assessment concepts (e.g., validity and reliability), classic test theory (Novick, 1966, Lord & Novick, 1968; Traub, 1997), and item response theory (Hambleton, Swaminathan, & Rogers, 1991). In addition, information about computational and probabilistic models that have been used to model cognitive aspects will be surveyed. These models include: cognitive diagnostic models (Rupp, Templin & Henson, 2010), Markov decision models (Feinberg & Shwartz, 2012; LaMar, 2018), Bayesian cognitive models (Almond, DiBello, Moulder & Zapata-Rivera, 2007; Conati, Gertner, & VanLehn, 2002; Lee & Wagenmakers, 2014; Levy & Mislevy, 2016), Bayesian knowledge tracing (Yudelson, Koedinger & Gordon, 2013), and Knowledge spaces (Falmagne et al., 2013).
Overall, we expect information about these concepts and models will level the playing field for people with different backgrounds so they will be prepared to benefit from the contents of the other chapters in the proposed volume. This presentation will describe the concepts and models that will be included in this section of the book. We will gather feedback from attendees on possible additions and modifications to the current outline.

Authors