Reading Task Classification Using EEG and Eye-Tracking Data

TL;DR

This study explores classifying reading tasks using EEG and eye-tracking data with machine learning, testing models at sentence and word levels across different subjects and datasets.

Contribution

It introduces models that classify reading tasks using both aggregated and fine-grained features, evaluated in within- and cross-subject scenarios on diverse datasets.

Findings

Models achieve above-chance accuracy in classifying reading tasks.

Fine-grained features improve classification performance.

Cross-subject generalization remains challenging.

Abstract

The Zurich Cognitive Language Processing Corpus (ZuCo) provides eye-tracking and EEG signals from two reading paradigms, normal reading and task-specific reading. We analyze whether machine learning methods are able to classify these two tasks using eye-tracking and EEG features. We implement models with aggregated sentence-level features as well as fine-grained word-level features. We test the models in within-subject and cross-subject evaluation scenarios. All models are tested on the ZuCo 1.0 and ZuCo 2.0 data subsets, which are characterized by differing recording procedures and thus allow for different levels of generalizability. Finally, we provide a series of control experiments to analyze the results in more detail.