Enhancing Classroom Assessment by Fusing Advanced Learning Technologies and Teaching Analytics: A Theoretically Driven Approach

• In Event: Toward a Theory of Classroom Assessment as the Regulation of Learning

Abstract

Today’s classrooms are dynamically changing environments, and teachers often do not get the data they need for decision making in a timely fashion and in a meaningful and actionable format. Teaching analytics is conceived as a subfield of learning analytics that focuses on the design, development, and evaluation of visual methods and tools for teachers. Teaching analytics methods and tools aim to develop innovative solutions to assist and augment teachers’ dynamic diagnostic decision-making. I argue that the effective classroom implementation of advanced learning technologies (e.g., intelligent, multi-agent systems) can be used to collect real-time data on students cognitive, affective, metacognitive, and motivational (CAMM) self-regulatory processes which are then used by both students to regulate their own learning and the same guide teachers in making just-in-time instructional decisions (Azevedo & Aleven, 2013).
This paper will examine the role of advanced learning technologies such as MetaTutor in augmenting teachers’ decision making by using visual tools embedded in cross-platform interfaces. These tools allow teachers to monitor and regulate their students’ knowledge and skills, and provide data for just-in-time decision making based on real-time CAMM processes collected during science learning (Azevedo et al., 2012, 2013). At the same time, such tools can provide students with real-time data about their peers’ CAMM processes during collaborative learning. For example, if a student has a panel (visualization tool) with information about his partners’ emotion (e.g., boredom) and motivation (e.g., lack of interest in the topic) then the student can use that data to encourage the partner to be more active in the collaborative problem solving activity.
The above scenario raises questions based on current models and theories of self-regulated learning (Hadwin et al., 2011; Pekrun, 2006; Winne & Hadwin, 2008) that will be explored: If the student does not know how to use such data, then what does the teacher do with that same data in terms of making instructional decisions, providing scaffolding and feedback, altering instructional sequence, etc.? How can complex data about emotions and motivation be presented to students as opposed to teachers? What is the visual metaphor to be used so that students and teachers can make decisions about them? Are the decisions accurate and how do they impact teaching and learning? How do data analytic tools and advanced learning technologies impact teachers’ training and practices, and classroom assessments?

Author

• Roger Azevedo, North Carolina State University