Using Real-Time Multichannel Self-Regulated Learning Data to Enhance Student Learning and Teachers' Decision Making With MetaDash

• In Event: Scaffolding Self-Regulation, Co-Regulation, and Socially Shared Regulation of Future Learning: Affordances of Learning Analytics Dashboards

Abstract

MetaDash is an intelligent, multichannel data visualization tool that displays key aspects of students’ learning processes and knowledge construction in real time, allowing for new innovations in adaptive learning and teaching. MetaDash extends current dashboards (see Verbert et al., 2013, 2014) by providing teachers with: (1) multichannel STEM learning and cognitive, affective, metacognitive, and motivational (CAMM) self-regulated learning (SRL) data collected from students while using existing advanced learning technologies (ALTs; e.g., intelligent tutoring systems), and (2) individual and aggregate data to accelerate their decision-making. Furthermore, contemporary interdisciplinary research presents ample evidence that the potential of ALTs to facilitate learning through real-time personalized instruction may be severely undermined by students’ inability to monitor and regulate key aspects of STEM learning, compounded by the lack of feedback and instruction on CAMM SRL processes (Authors, Date). The ultimate goal of MetaDash is to foster STEM learning with a ubiquitous, multilayered system that fosters teachers’ and students’ monitoring and control of CAMM SRL processes during teaching and learning of complex STEM topics.
Our project will build a theoretically and data-driven technological tool that will help students and teachers understand how students’ CAMM SRL processes can be leveraged to promote conceptual understanding (e.g., Authors, Date; Authors, Date). MetaDash will allow an interdisciplinary research team to use interdisciplinary methodologies to detect, track, model, and assess students’ CAMM SRL processes and teachers’ use of these data to understand and foster SRL. This work will be important for advancing current scientific research in STEM by: (1) enhancing current theoretical models of SRL with ALTs; (2) extending current interdisciplinary research methods and analytical techniques to detect, track, and model the complex nature of CAMM SRL processes and STEM learning; and (3) conducting empirical research to examine how providing real-time multichannel data to teachers can enhance instructional decision-making through the use of a new genre of technology.
Preliminary data from teachers’ reveals critical issues related to the presentation and timing of students’ CAMM SRL data. For example, videos of students’ facial expressions need to be collected, analyzed, and re-presented as a dynamic pie charts that show aggregate (classroom-level) affective data. In contrast, evidence of students’ metacognitive monitoring accuracy is more challenging to collect in real-time (via log-files and human-machine interactions) and require more abstract yet actionable representations for teachers’ ease of interpretability and use. Our paper will focus on the presentation of emerging data related to the challenges associated with the collection, analyses, (re-) presentation, timing, and interpretability of students’ CAMM SRL processes for teachers using MetaDash.
With MetaDash, we aim to: (1) foster deep conceptual understanding in STEM, (2) increase teachers’ capacity for fostering effective SRL and STEM learning, and (3) develop a technological tool that can scale to classrooms across the country, and automatically generated analyses for teachers, school administrators, and parents. Effective applications of MetaDash in formal and informal educational settings can significantly enhance STEM learning across students of all ages.

Authors

• Roger Azevedo, North Carolina State University

• Min Chi, Stanford University

• Soonhye Park, North Carolina State University

• Michelle Taub, North Carolina State University