A Discriminative Model for Identifying Readers and Assessing Text Comprehension from Eye Movements
This work addresses reader identification for applications like personalized learning or security, but it is incremental as it builds on existing eye-tracking and kernel methods.
The paper tackled the problem of inferring readers' identities and estimating text comprehension from eye movements, developing a generative model and Fisher-SVM approach; it found that the method excelled at identifying readers but failed to accurately estimate comprehension.
We study the problem of inferring readers' identities and estimating their level of text comprehension from observations of their eye movements during reading. We develop a generative model of individual gaze patterns (scanpaths) that makes use of lexical features of the fixated words. Using this generative model, we derive a Fisher-score representation of eye-movement sequences. We study whether a Fisher-SVM with this Fisher kernel and several reference methods are able to identify readers and estimate their level of text comprehension based on eye-tracking data. While none of the methods are able to estimate text comprehension accurately, we find that the SVM with Fisher kernel excels at identifying readers.