Advancing log analysis of student interactions with cognitive tools

We have developed a software application (gStudy) that supports learning with multimedia documents. Students use gStudy to create and link notes, highlight and label text and images, construct glossaries and concept maps, exchange information objects through a chat interface, and perform other operations on multimedia content. The detailed log files recorded by gStudy constitute a wealth of data about how students process information as they learn. In this paper we describe log parsing and data mining methods we have borrowed from computer science and apply to researching self-regulated learning. The analysis software we developed identifies coherent learner actions from the complex series of low-level events recorded by gStudy and detects sequential patterns of these actions that may be interspersed with unrelated actions. It applies a data mining algorithm to discover action patterns which are the longest subsequences common to a group of participants. The use of these methods is illustrated through an analysis of gStudy log files generated by 103 university students. Log Analysis of Student Interactions with Cognitive Tools 3 gStudy is a software application for researching self-regulated learning (Winne et al., 2006). Learners use gStudy to operate on multimedia documents packaged in learning kits. Because gStudy presents documents through a web browser, learning kits may contain media commonly found on the web such as text, video, diagrams, and animations. As learners work in a learning kit, they use gStudy tools to create information objects and hyperlinks connecting them. Learners can highlight and categorize selections of content. They can create notes, glossary entries, concept maps, HTML documents and other objects. Learners can collaborate with others through a chat tool, sharing the information objects they create. To make a note linked to content in a learning kit a learner chooses a note template. Note templates are schemas that instructional designers, teachers, researchers or learners can design to structure the note content. Note templates are often designed to scaffold cognitive or metacognitive processing. Creating a note as guided by a template in gStudy is an instance of using a tool for learning. As a learner uses this tool, gStudy records in detail the events involved in creating a note: which content was selected, when the selection was made, which note template the learner chose, which fields of the note template the learner filled in, what information was entered in those fields, and when the learner closed the note window. All these …