A framework for identifying working memory capacity from the log information of learning systems

Working memory capacity (WMC) is a cognitive trait that affects students' learning behaviors to perform complex cognitive tasks such as reading comprehension, problem solving, and making decision. Considering students' WMC when providing them with course materials and activities helps in avoiding cognitive overload and therefore positively affects students' learning. However, in order to consider students' WMC in the learning process, an approach is needed to identify students' WMC. To address this problem, we introduce a general framework to automatically identify WMC from students' behavior in a learning system. Our approach is generic and designed to work with different learning systems. It connects to the learning systems' database and extracts students' behavior data to analyze them for indications about their WMC. The proposed approach has been implemented as an extension to a tool for detecting learning styles, enabling this tool to additionally identify students' WMC. By knowing students' WMC, teachers can provide meaningful recommendations to support students with low and high WMC. Furthermore, such information is the basis for designing adaptive systems that can automatically provide students with individualized support based on their WMC.