A Discriminative Model for Identifying Readers and Assessing Text Comprehension from Eye Movements
Abstract
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.
Cite
Text
Makowski et al. "A Discriminative Model for Identifying Readers and Assessing Text Comprehension from Eye Movements." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2018. doi:10.1007/978-3-030-10925-7_13Markdown
[Makowski et al. "A Discriminative Model for Identifying Readers and Assessing Text Comprehension from Eye Movements." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2018.](https://mlanthology.org/ecmlpkdd/2018/makowski2018ecmlpkdd-discriminative/) doi:10.1007/978-3-030-10925-7_13BibTeX
@inproceedings{makowski2018ecmlpkdd-discriminative,
title = {{A Discriminative Model for Identifying Readers and Assessing Text Comprehension from Eye Movements}},
author = {Makowski, Silvia and Jäger, Lena A. and AbdelWahab, Ahmed and Landwehr, Niels and Scheffer, Tobias},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2018},
pages = {209-225},
doi = {10.1007/978-3-030-10925-7_13},
url = {https://mlanthology.org/ecmlpkdd/2018/makowski2018ecmlpkdd-discriminative/}
}