Keywords
Eye Tracking, Eye movement analysis, Learning outcome prediction
Abstract
E-Learning is emerging as a convenient and effective learning tool. However, the challenge with eLearning is the lack of effective tools to assess levels of learning. Ability to predict difficult content in real time enables eLearning systems to dynamically provide supplementary content to meet learners’ needs. Recent developments have made possible low-cost eye trackers, which enables a new class of applications based on eye response. In comparison to past attempts using bio-metrics in learning assessments, with eye tracking, we can have access to the exact stimulus that is causing the response. A key aspect of the proposed approach is the temporal analysis of eye response and stimulus (concept) that is causing the response. Variations in eye response to the same concept over time may be indicative of levels of learning. The proposed system analyses slide images to extract words and then maps eye response to those words. We propose an analytical model (refer figure 1) for predicting various levels of learning in real time and the model achieves a prediction accuracy of 70%.
Start Date
18-5-2017 3:48 PM
End Date
18-5-2017 4:10 PM
REAL TIME LEARNING LEVEL ASSESSMENT USING EYE TRACKING
E-Learning is emerging as a convenient and effective learning tool. However, the challenge with eLearning is the lack of effective tools to assess levels of learning. Ability to predict difficult content in real time enables eLearning systems to dynamically provide supplementary content to meet learners’ needs. Recent developments have made possible low-cost eye trackers, which enables a new class of applications based on eye response. In comparison to past attempts using bio-metrics in learning assessments, with eye tracking, we can have access to the exact stimulus that is causing the response. A key aspect of the proposed approach is the temporal analysis of eye response and stimulus (concept) that is causing the response. Variations in eye response to the same concept over time may be indicative of levels of learning. The proposed system analyses slide images to extract words and then maps eye response to those words. We propose an analytical model (refer figure 1) for predicting various levels of learning in real time and the model achieves a prediction accuracy of 70%.