The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data

Frontiers in Psychology

article

Nora Hollenstein¹  Marius Tröndle²  Martyna Plomecka²  Samuel Kiegeland³  Yilmazcan Özyurt³  Lena A. Jäger⁴  Nicolas Langer² 

[1] Center for Language Technology, University of Copenhagen;Department of Psychology, University of Zurich;Department of Computer Science;Department of Computational Linguistics, University of Zurich;Department of Computer Science, University of Potsdam

关键词: reading task classification;    Eye-tracking;    EEG;    machine learning;    reading research;   

DOI  :  10.3389/fpsyg.2022.1028824

学科分类：社会科学、人文和艺术（综合）

来源: Frontiers

【 摘 要 】

We present a new machine learning benchmark for reading task classification with the goal of advancing EEG and eye-tracking research at the intersection between computational language processing and cognitive neuroscience. The benchmark task consists of a cross-subject classification to distinguish between two reading paradigms: normal reading and task-specific reading. The data for the benchmark is based on the Zurich Cognitive Language Processing Corpus (ZuCo 2.0), which provides simultaneous eye-tracking and EEG signals from natural reading of English sentences. The training dataset is publicly available, and we present a newly recorded hidden testset. We provide multiple solid baseline methods for this task and discuss future improvements. We release our code and provide an easy-to-use interface to evaluate new approaches with an accompanying public leaderboard: www.zuco-benchmark.com.

【 授权许可】

CC BY