Remote Measures of Attention and Affect: Online Data Collection in the Age of COVID-19

Session Type: Symposium

Abstract

Effective educational research relies on data collection to both understand the learning process and assesses learning outcomes. Key to the former is understanding how a student’s affective and cognitive states are impacted by an intervention. The response to COVID-19 has made it difficult for educational researchers to use traditional approaches for collecting this type of data as classroom observations and interviews have become impractical. This symposium will explore a variety of approaches to measuring frustration, attention, engagement, and other affective and cognitive states critical for understanding the learning process. Research teams from a variety of academic institutions will share their approach to tackling this challenge. Explored methods include behavior analysis, facial emotion recognition, eye tracking, and educational data mining.

Sub Unit

• SIG-Advanced Technologies for Learning

Chair

• Ibrahim Dahlstrom-Hakki, TERC

Papers

• Detecting Learners' Frustration Based on Their Performance in Game-Based Learning Activities - Maya Israel, University of Florida; Tongxi Liu, University of Florida

• Identifying Frustration Moments Using Facial Emotion Recognition and Behavioral Data Mining - Fengfeng Ke, Florida State University; Jewoong Moon, Florida State University

• Differentiating Between Unproductive and Productive Persistence in an Educational Game Using Behavioral Data - Mia Almeda, TERC; Jodi Asbell-Clarke, TERC; Elizabeth Rowe, TERC

• The Viability of Using Remote Webcam-Based Eye Tracking to Monitor Attention Allocation in Educational Research - Ibrahim Dahlstrom-Hakki, TERC; Fengfeng Ke, Florida State University; Ruohan Liu, University of Florida; Zlatko Sokolikj, Florida State University

Discussant

• Sidney K. D'Mello, University of Colorado - Boulder