Skip to main Communities My dashboard Log in Sign up There is a newer version of the record available. Published April 16, 2026 | Version v2 Dataset Restricted EmoRoad: A Multimodal Dataset of Psychological, Physiological, and Behavioral Responses in Diverse Driving Scenarios Authors/Creators CHAI, Bo 1 ZHANG, Mingyuan 1 LIU, Meichen 1 FANG, Le 1 CHEN, Ziyi 1 GONG, Wei 1 JIN, Shuting 1 SENTHIL KUMAR, Gokula Manikandan 1 CHEN, Xingtong 1 WANG, Jia Stephen (Supervisor) 1 Show affiliations 1. Hong Kong Polytechnic University Description Overview This dataset is a multimodal dataset collected under multiple driving tasks and conditions. It includes data from 50 participants and 8 driving tasks defined by a 2 × 2 × 2 factorial design: weather (2 levels), traffic volume (2 levels), and road scenario (2 levels). The recorded modalities include: facial video, in-car first-person screen recordings, car dynamics (e.g., speed, acceleration, etc.), EmoSense (steering-wheel touch sensor), EEG, eye tracking, and emotion annotations from both iMotions and participant self-reports. The dataset supports research on emotion and behavior modeling and analysis, and driving context's effects on emotion and behavior, with potential applications in driver state monitoring and adaptive vehicle system. Contents & file organization The upload contains two top-level folders: `Clip/` and `RawData/`. Clip/ `Clip/` provides task-aligned (clipped) data for all modalities. All signals/videos are clipped according to the valid driving-task start and end timestamps. The corresponding timestamps and helper code are provided in `ref_timestamp.py` in our GitHub repository (see “Repository URL” in this record). For EEG data in `Clip/`, we provide a preprocessed version with artifacts removed using ICA and amplitude-thresholding. The preprocessing scripts are also available in the GitHub repository. RawData/ `RawData/` provides representative raw recordings (including raw EEG), enabling users to apply their preferred preprocessing pipelines. Folder structure The overall folder structure is illustrated below. Data are organized by modality under `Clip/` or `RawData/`, using the prefix `Clip_` or `RawData_` followed by the modality name. Within each modality folder, data are organized as: - `P1/`–`P50/` (participants) - 8 driving tasks per participant, each containing the corresponding recordings for that task. Clip/ ├─ Clip_Car_Dynamics/ ├─ Clip_EEG_noArtifact_icaCUS_thr100/ │ ├─ P1/ │ │ ├─ 0925_p1_1.csv │ │ ├─ 0925_p1_2.csv │ │ ├─ ... │ │ └─ 0925_p1_8.csv │ ├─ P2/ │ ├─ ... │ └─ P50/ ├─ Clip_EmoSense/ ├─ ... └─ Clip_ScreenRecord/ RawData/ ├─ RawData_Car_Dynamics/ ├─ RawData_EEG/ ├─ RawData_EmoSense/ ├─ RawData_FacialRecord/ └─ RawData_iMotions/ Notes Access notice: This dataset is available under restricted access. To request access, please use the Zenodo “Request access” function on this record. By requesting access to, downloading, or using the dataset, applicants/users agree to comply with the Data Usage Agreement (DUA). Please review the public summary below. The full DUA will be provided to approved applicants as part of the controlled-access process; in the event of any discrepancy, the full DUA shall prevail. Other Terms of Access / Data Usage Agreement (DUA) — Public Summary Dataset: EmoRoad Multimodal Dataset (controlled access; includes identifiable or potentially re-identifiable human data such as facial videos and related behavioural/physiological signals) Data controller/provider: Prof. Stephen Jia Wang, The Hong Kong Polytechnic University (PolyU) DUA version/date: v3 (28/06/2026) By requesting access to, downloading, or using any part of this dataset, the Data User agrees to the following key terms: 1) Permitted use (internal research/analysis only) Use is permitted for legitimate internal research and analysis, including methodological development and evaluation, in academic or commercial research settings, subject to compliance with applicable laws and institutional policies. The dataset must not be redistributed, in whole or in part, to any person or entity not covered by an applicable access agreement. The dataset must not be provided, in whole or in part, as a product, service, or hosted dataset offering. The dataset must not be used in any manner that would enable participant re-identification, participant contact, or disclosure of identifiable raw data. 2) No re-identification and no participant interaction No attempts may be made to identify or re-identify participants, including by linking with other datasets or using biometric identification techniques such as face or voice recognition. Participants must not be contacted or approached in any way. If a participant’s identity is learned accidentally, the user must cease analyses using identified information, must not record or disclose the identity, and must notify the provider. 3) Data security and access control The dataset must be stored and processed on secure, access-controlled systems, such as institutional servers or encrypted storage. Access must be limited to authorised personnel working on the authorised project, and all such personnel must be informed of and comply with these terms. The dataset must not be stored on public or insecure services or exposed through publicly shared links. 4) No redistribution / onward sharing The dataset, in whole or in part, must not be shared or redistributed to any person, group, or platform not covered by an approved access agreement. External collaborators must submit their own access request and agree separately to the applicable DUA. 5) Outputs, publication, and citation Only derived, non-identifiable outputs may be shared, such as aggregate statistics, plots, evaluation metrics, or trained model outputs. Shared outputs must not enable re-identification or disclose identifiable raw data, including identifiable video frames or raw signals that could compromise participant privacy. Publications, preprints, presentations, or derivative works using the dataset must properly cite the dataset and any associated dataset paper, data descriptor, or other relevant publication where available, following the citation information provided on the repository landing page where possible. The data provider(s) and participants must not be presented as endorsing the user’s findings, methods, or interpretations. 6) Incident reporting The provider must be notified promptly of any suspected or actual data breach, data loss, unauthorised access, or accidental re-identification risk. Users must take reasonable steps to mitigate any such incident and cooperate with reasonable requests aimed at reducing participant risk. 7) Duration, termination, and deletion Access may be revoked if the terms are breached or if continued access would pose unacceptable ethical, legal, or security risks. Upon request or termination, all copies of the dataset, including backups, must be deleted or irreversibly destroyed, and deletion must be confirmed if requested. Access procedure Use the “Request access” function on this Zenodo record. Provide name, affiliation, and a verifiable contact email and/or ORCID. Confirm agreement to the DUA terms above. Full agreement The full Data Usage Agreement will be provided to approved applicants as part of the controlled-access process and is included in the repository files as 00_Data_Usage_Agreement_v3.pdf . Files Restricted The record is publicly accessible, but files are restricted. Log in to check if you have access. Additional details Software Repository URL https://github.com/chaizufeng/EmoRoad-Dataset Programming language Python , MATLAB 390 Views 107 Downloads Show more details All versions This version Views Total views 390 153 Downloads Total downloads 107 67 Data volume Total data volume 82.1 TB 81.3 TB More info on how stats are collected.... Versions External resources Indexed in OpenAIRE Communities Details DOI DOI Badge DOI 10.5281/zenodo.19641357 Markdown [](https://doi.org/10.5281/zenodo.19641357) reStructuredText .. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.19641357.svg :target: https://doi.org/10.5281/zenodo.19641357 HTML <a href="https://doi.org/10.5281/zenodo.19641357"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.19641357.svg" alt="DOI"></a> Image URL https://zenodo.org/badge/DOI/10.5281/zenodo.19641357.svg Target URL https://doi.org/10.5281/zenodo.19641357 Resource type Dataset Publisher Zenodo Rights License Creative Commons Attribution 4.0 International The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited. Read more Citation Export Technical metadata Created April 18, 2026 Modified June 28, 2026 Jump up About About Policies Infrastructure Principles Projects Roadmap Contact Blog Blog Support Help FAQ Developers REST API OAI-PMH Contribute GitHub Donate Funded by Powered by CERN Data Centre & InvenioRDM Status Privacy policy Cookie policy Terms of Use This site uses cookies. Find out more on how we use cookies Accept all cookies Accept only essential cookies