Prediction of Users' Learning Curves for Adaptation while Using an Information Visualization

Abstract

User performance and satisfaction when working with an interface is influenced by how quickly the user can acquire the skills necessary to work with the interface through practice. Learning curves are mathematical models that can represent a user's skill acquisition ability through parameters that describe the user's initial expertise as well as her learning rate. This information could be used by an interface to provide adaptive support to users who may otherwise be slow in learning the necessary skills. In this paper, we investigate the feasibility of predicting in real time a user's learning curve when working with ValueChart, an interactive visualization for decision making. Our models leverage various data sources (a user's gaze behavior, pupil dilation, cognitive abilities), and we show that they outperform a baseline that leverages only knowledge on user task performance so far. We also show that the best performing model achieves good accuracies in predicting users' learning curves even after observing users' performance only on a few tasks. These results are promising toward the design of user-adaptive visualizations that can dynamically support a user in acquiring the necessary skills to complete visual tasks.

What Does Your Gaze Reveal About You? On the Privacy Implications of Eye Tracking

“…It should be acknowledged that many of the cited inference methods were only tested under controlled laboratory conditions and lack evaluation in real-world scenarios [4,18,27,52,65,67,69,86,88]. On the other hand, it may reasonably be assumed that some of the companies with access to eye tracking data from consumer devices (e.g., device manufacturers, ecosystem providers) possess larger sets of training data, more technical expertise, and more financial resources than the researchers cited in this paper.…”

“…In some fields, eye tracking has not only been used as a tool to discriminate between people of different skill levels, but also to predict people's task performance and learning curves [52,69] and to examine specific learning disabilities, such as mathematical difficulties and dyslexia [31,85].…”

Assessing cognitive load using oculometrics to identify deceit during interviews

“…Average Percentage Change in Pupil Size (APCPS ; Iqbal et al, ; Lallé et al, ; Iqbal et al, ). The Percentage Change in Pupil Size (PCPS) is calculated as the difference between the measured pupil size and the baseline pupil size, divided by the baseline pupil size.…”

“…Since 1964, researchers have known that pupil size changes in response to mental activity (Hess & Polt, ). Currently, data regarding changes in pupil diameter, measured with eye‐tracking technology, are widely used to study cognitive load tasks such as driving a vehicle while listening to a dialogue (Kun, Palinko, Medenica, & Heeman, ), interacting with interfaces for decision making (Lallé, Toker, Conati, & Carenini, ), doing math exercises, memorizing numbers, and perceiving visual stimuli (Beatty, ), and performing mental arithmetic (Chen, Epps, & Chen, ), among others.…”

“…As a result, a percentage of pupil size variability based on a baseline calculation can be due to ethnic differences. In order to overcome this limitation, two pupillary metrics of cognitive load, Mean Pupil Diameter Change (MPDC; Kun et al, ; Palinko & Kun, ; Palinko, Kun, Shyrokov, & Heeman, ) and Average Percentage Change in Pupil Size (APCPS; Iqbal, Zheng, & Bailey, ; Iqbal, Adamczyk, Zheng, & Bailey, ; Lallé et al, ), were selected for our experiment. These specific metrics are the most suitable for the Caucasian and Asian eyes presented in Mexico.…”