The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data
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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2022.1028824/full |
| _version_ | 1797955194850377728 |
|---|---|
| author | Nora Hollenstein Marius Tröndle Martyna Plomecka Samuel Kiegeland Yilmazcan Özyurt Lena A. Jäger Lena A. Jäger Nicolas Langer |
| author_facet | Nora Hollenstein Marius Tröndle Martyna Plomecka Samuel Kiegeland Yilmazcan Özyurt Lena A. Jäger Lena A. Jäger Nicolas Langer |
| author_sort | Nora Hollenstein |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-10T23:29:40Z |
| format | Article |
| id | doaj.art-3bc0f21de40a463d8b1af02f41ae88b1 |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-04-10T23:29:40Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-3bc0f21de40a463d8b1af02f41ae88b12023-01-12T07:02:21ZengFrontiers Media S.A.Frontiers in Psychology1664-10782023-01-011310.3389/fpsyg.2022.10288241028824The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking dataNora Hollenstein0Marius Tröndle1Martyna Plomecka2Samuel Kiegeland3Yilmazcan Özyurt4Lena A. Jäger5Lena A. Jäger6Nicolas Langer7Center for Language Technology, University of Copenhagen, Copenhagen, DenmarkDepartment of Psychology, University of Zurich, Zurich, SwitzerlandDepartment of Psychology, University of Zurich, Zurich, SwitzerlandDepartment of Computer Science, ETH Zurich, Zurich, SwitzerlandDepartment of Computer Science, ETH Zurich, Zurich, SwitzerlandDepartment of Computational Linguistics, University of Zurich, Zurich, SwitzerlandDepartment of Computer Science, University of Potsdam, Potsdam, GermanyDepartment of Psychology, University of Zurich, Zurich, SwitzerlandWe 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.https://www.frontiersin.org/articles/10.3389/fpsyg.2022.1028824/fullreading task classificationeye-trackingEEGmachine learningreading researchcross-subject evaluation |
| spellingShingle | Nora Hollenstein Marius Tröndle Martyna Plomecka Samuel Kiegeland Yilmazcan Özyurt Lena A. Jäger Lena A. Jäger Nicolas Langer The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data Frontiers in Psychology reading task classification eye-tracking EEG machine learning reading research cross-subject evaluation |
| title | The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data |
| title_full | The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data |
| title_fullStr | The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data |
| title_full_unstemmed | The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data |
| title_short | The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data |
| title_sort | zuco benchmark on cross subject reading task classification with eeg and eye tracking data |
| topic | reading task classification eye-tracking EEG machine learning reading research cross-subject evaluation |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2022.1028824/full |
| work_keys_str_mv | AT norahollenstein thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT mariustrondle thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT martynaplomecka thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT samuelkiegeland thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT yilmazcanozyurt thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT lenaajager thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT lenaajager thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT nicolaslanger thezucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT norahollenstein zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT mariustrondle zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT martynaplomecka zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT samuelkiegeland zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT yilmazcanozyurt zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT lenaajager zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT lenaajager zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata AT nicolaslanger zucobenchmarkoncrosssubjectreadingtaskclassificationwitheegandeyetrackingdata |