Resources

The tutorial introduces a growing research area that combines eye tracking during reading with NLP. It outlines how eye movements in reading can be leveraged for NLP, and, vice versa, how NLP methods can advance psycholinguistic modeling of eye movements in reading. We cover four main themes: (i) fundamentals of eye movements in reading, (ii) experimental methodologies and available data, (iii) integrating eye movement data in NLP models, and (iv) using NLP for modeling eye movements in reading. The tutorial is tailored to NLP researchers and practitioners, and provides the essential background for conducting research on joint modeling of eye movements and text.

 

EyeBench v1.0. The benchmark curates multiple datasets for predicting reader properties, and reader–text interactions from eye movements. :star: marks prediction tasks newly introduced in EyeBench. The data are preprocessed and standardized into aligned text and gaze sequences, which are then used as input to models trained to predict task-specific targets. The models are systematically evaluated under three generalization regimes — unseen readers, unseen texts, or both. The benchmark supports the evaluation and addition of new models, datasets, and tasks.

Python re-implementation of the working memory capacity (WMC) battery described by Lewandowsky at al. here. This implementation is a minute reproduction of the original MATLAB implementation and uses the same file output format for compatibility with accompanying scripts of the original implementation.

Various labs participating in the MultiplEYE COST Action already use this software, check it out!

The Python package pymovements allows for easily preprocessing and working with eye-tracking data. It features different preprocessing algorithms that can be freely chosen and parametrized by the user, integrates an interface to download and work with existing datasets, and many other features. Check it out!

A naturalistic eye-movements-while-reading corpus of 107 native English speakers reading machine-generated texts.

Click here for more details on how to use and how to cite this corpus!

A naturalistic eye-tracking-while-reading corpus containing data from 75 participants reading 12 scientific texts.

Click here for more details on how to use and how to cite this corpus!

We're aiming at sharing our knowledge and making it accessible for other researchers or lay people. This is why we contribute and create tutorials to be shared with everyone!

Our labs has lead or contributed to a variety of different eye-tracking datasets. Find all of our datasets below:

We have created an overview on existing eye-tracking-while-reading datasets. You can find the overview neatly presented in a filterable table!