Reading Task Classification Using EEG and Eye-Tracking Data
This work addresses the challenge of understanding cognitive processes during reading for researchers in neuroscience and human-computer interaction, but it appears incremental as it applies existing machine learning methods to a new dataset without introducing novel paradigms.
The researchers tackled the problem of classifying reading tasks (normal vs. task-specific) using EEG and eye-tracking data from the ZuCo corpus, achieving classification results that varied across different feature types and evaluation scenarios, with specific accuracy numbers reported for within-subject and cross-subject conditions.
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.