Measuring causality between collaborative and individual gaze metrics for collaborative problem‐solving with intelligent tutoring systems

Kshitij Sharma,Vincent Aleven,Jennifer K Olsen,Nikol Rummel

doi:10.1111/jcal.12467

Abstract

AbstractWhen students are working collaboratively and communicating verbally in a technology‐enhanced environment, the system cannot track what collaboration is happening outside of the technology, making it difficult to fully assess the collaboration of the students and adapt accordingly. In this article, we propose using gaze measures as a proxy for cognitive processes to achieve collaboration awareness. Specifically, we use Granger causality to analyse the causal relationships between collaborative and individual gaze measures from students working on a fractions intelligent tutoring system and the influence that the students' dialogue, prior knowledge, or success has on these relationships. We found that collaborative gaze patterns drive the individual focus in the pairs with high posttest scores and when they are engaged in problem‐solving dialogues but the opposite with low performing students. Our work adds to the literature by extending the correlational relationships between individual and collaborative gaze measures to causal relationships and suggests indicators that can be used within an adaptive system.

Highlights

As learning technology and data collection advances, researchers have been able to produce more accurate models of students' current states and understandings to provide better learning support
We investigate the causal relationships between students' individual and collaborative cognitive processes, using gaze patterns as a proxy, for primary school students working on a collaborative fractions intelligent tutoring systems (ITSs) and examine how their dialogue plays a role in this relationship
We investigate the causal relationships between students' individual and collaborative cognitive processes, using gaze patterns as a proxy, for elementary school students working on a collaborative fractions ITS and examine how their dialogue plays a role in this relationship over time

Summary

Introduction

As learning technology and data collection advances, researchers have been able to produce more accurate models of students' current states and understandings to provide better learning support. For the collaboration to be beneficial, like with any skill, students must learn how to collaborate (Rummel & Spada, 2005), making it important for learning technologies to provide social support in addition to the cognitive learning support (Weinberger, Ertl, Fischer, & Mandl, 2005) that students need to be successful. They do not all start with the same expectations about collaboration, and adaptive collaborative learning support (ACLS) may be needed to provide students with the correct support at the correct time (Magnisalis, Demetriadis, & Karakostas, 2011; Walker, Rummel, & Koedinger, 2011). ACLS can be used to adapt to the collaborative learning environment to provide appropriate support

Objectives

Methods

Results

Discussion

Conclusion