{"dataset":{"id":"61106","dataset_id":"on005540","name":"EmoEEG-MC: A Multi-Context Emotional EEG Dataset for Cross-Context Emotion Decoding","description":"EmoEEG-MC is a multi-context emotional EEG dataset comprising 64-channel EEG and peripheral physiological recordings (PPG, GSR) from 60 participants exposed to video-induced and imagery-induced emotional stimuli. Seven emotion categories (joy, inspiration, tenderness, fear, disgust, sadness, neutral) were evoked and validated through subjective reports, enabling investigation of cross-context emotion decoding. The dataset supports research on neural mechanisms of emotion and generalization of affective computing models across contexts.","owner_user_id":15,"status":"active","github_repo":"nemarDatasets/on005540","concept_doi":"10.82901/nemar.on005540","latest_version_doi":"10.82901/nemar.on005540.v1.0.0","created_at":"2026-06-27 08:31:00","updated_at":"2026-08-19 01:31:42","zenodo_concept_id":null,"is_sandbox":0,"visibility":"public","ezid_status":"public","enrichment_json":"{\n  \"version\": \"2.0\",\n  \"pipeline_stage\": \"validated\",\n  \"title\": \"EmoEEG-MC: A Multi-Context Emotional EEG Dataset for Cross-Context Emotion Decoding\",\n  \"description\": \"EmoEEG-MC is a multi-context emotional EEG dataset comprising 64-channel EEG and peripheral physiological recordings (PPG, GSR) from 60 participants exposed to video-induced and imagery-induced emotional stimuli. Seven emotion categories (joy, inspiration, tenderness, fear, disgust, sadness, neutral) were evoked and validated through subjective reports, enabling investigation of cross-context emotion decoding. The dataset supports research on neural mechanisms of emotion and generalization of affective computing models across contexts.\",\n  \"methods_description\": \"EEG (64-channel) and peripheral physiological data (PPG, GSR) were recorded from 60 participants during two experimental contexts: video-induced and imagery-induced emotion elicitation, covering seven emotion categories. Subjective reports were used to validate the emotional experience for each category. Some participants have incomplete trial sets due to missing imagery or video trials.\",\n  \"license\": \"CC0\",\n  \"dataset_type\": \"raw\",\n  \"authors\": {\n    \"Xin XU\": {},\n    \"Xinke SHEN\": {},\n    \"Xuyang CHEN\": {},\n    \"Qingzhu ZHANG\": {},\n    \"Sitian WANG\": {},\n    \"Yihan LI\": {},\n    \"Zongsheng LI\": {},\n    \"Dan ZHANG\": {\n      \"orcid\": \"0000-0002-7592-3200\"\n    },\n    \"Mingming ZHANG\": {},\n    \"Quanying LIU\": {}\n  },\n  \"keywords\": [\n    {\n      \"term\": \"EEG\"\n    },\n    {\n      \"term\": \"Emotions\",\n      \"subject_scheme\": \"MeSH\",\n      \"value_uri\": \"http://id.nlm.nih.gov/mesh/D004644\"\n    },\n    {\n      \"term\": \"affective computing\"\n    },\n    {\n      \"term\": \"emotion decoding\"\n    },\n    {\n      \"term\": \"cross-context generalization\"\n    },\n    {\n      \"term\": \"peripheral physiological signals\"\n    }\n  ],\n  \"related_identifiers\": [\n    {\n      \"identifier\": \"https://github.com/nemarDatasets/on005540\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"https://nemar.org/dataset/on005540\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"10.1038/s41597-023-02650-w\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"References\"\n    },\n    {\n      \"identifier\": \"10.1073/pnas.1321664111\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"References\"\n    },\n    {\n      \"identifier\": \"10.18112/openneuro.ds005540.v1.0.7\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsDerivedFrom\"\n    }\n  ],\n  \"funding_references\": [\n    {\n      \"funder_name\": \"National Key R&D Program of China\",\n      \"award_number\": \"2021YFF1200804\"\n    },\n    {\n      \"funder_name\": \"Shenzhen Excellent Youth Project\",\n      \"award_number\": \"RCYX20231211090405003\"\n    },\n    {\n      \"funder_name\": \"Shenzhen Science and Technology Innovation Committee\",\n      \"award_number\": \"RCBS20231211090748082, KJZD20230923115221044, 2022410129, KCXFZ20201221173400001\"\n    },\n    {\n      \"funder_name\": \"SUSTech Undergraduate Innovation and Entrepreneurship Training Program\",\n      \"award_number\": \"2024S07\"\n    }\n  ],\n  \"resource_type_general\": \"Dataset\",\n  \"resource_type_specific\": \"Neuroimaging Dataset\",\n  \"modalities\": [\n    \"beh\",\n    \"eeg\"\n  ],\n  \"sizes\": [\n    \"75.6 GB (1077 files)\"\n  ],\n  \"formats\": [\n    \".4593\",\n    \".csv\",\n    \".edf\",\n    \".gz\",\n    \".ipynb\",\n    \".json\",\n    \".mat\",\n    \".md\",\n    \".npy\",\n    \".pth\",\n    \".py\",\n    \".pyc\",\n    \".tsv\",\n    \".txt\",\n    \".xlsx\",\n    \".yml\"\n  ],\n  \"source_hash\": \"af17f4085375b44bf367ae2633f9f5a1175a4e55dfbfe862c99bc8a75f4d7cc2\"\n}","last_activity_at":"2026-06-27 08:31:00","source":"openneuro","source_id":"ds005540","subject_count":60,"modalities":"beh,eeg","age_min":18,"age_max":26,"file_size":75594349634,"total_files":1311,"tasks":"emotion","metadata_columns_error":null,"staleness_warn_stage":null,"staleness_admin_notified_at":null,"authors":"Xin XU, Xinke SHEN, Xuyang CHEN, Qingzhu ZHANG, Sitian WANG, Yihan LI, Zongsheng LI, Dan ZHANG, Mingming ZHANG, Quanying LIU","license":"CC0","readme":"[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.on005540-blue)](https://doi.org/10.82901/nemar.on005540)\n\n# EmoEEG-MC: A Multi-Context Emotional EEG Dataset for Cross-Context Emotion Decoding\r\n\r\n## Authors\r\n\r\nXin XU[^1,†], Xinke SHEN[^1,†,*], Xuyang CHEN[^1], Qingzhu ZHANG[^1], Sitian WANG[^1], Yihan LI[^1], Zongsheng LI[^1,^2], Dan ZHANG[^3], Mingming ZHANG[^1], Quanying LIU[^1,*]\r\n\r\n[^1]: Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, 518055, China  \r\n[^2]: School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, 518172, China  \r\n[^3]: Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, 100084, China  \r\n\r\n*Corresponding authors:* Quanying LIU (liuqy@sustech.edu.cn); Xinke SHEN (shenxk@sustech.edu.cn)  \r\n† These authors contributed equally to this work.\r\n\r\n---\r\n\r\n## Abstract\r\n\r\nDecoding emotions using electroencephalography (EEG) is gaining increasing attention due to its objectivity in measuring emotional states. However, the ability of existing EEG-based emotion decoding methods to generalize across different contexts remains underexplored, as most approaches are trained and evaluated only within a single context. Studying emotions across multiple contexts is essential for advancing our understanding of the neural mechanisms underlying emotional processing and enhancing the real-world applicability of affective computing systems.\r\n\r\nA key limitation in this field is the lack of EEG datasets designed specifically to capture emotional responses across diverse contexts. To address this gap, we present the **Multi-Context Emotional EEG (EmoEEG-MC) dataset**, featuring 64-channel EEG and peripheral physiological data from 60 participants exposed to two distinct contexts: video-induced and imagery-induced emotions. These contexts evoke seven distinct emotional categories: joy, inspiration, tenderness, fear, disgust, sadness, and neutral emotion. The emotional experience of a specific emotion category was validated through subjective reports.\r\n\r\nUsing Support Vector Machines (SVMs) with L1 regularization, we achieved cross-context emotion decoding accuracies of 66.7% for binary classification (positive vs. negative emotions) and 28.9% for seven-category emotion classification, both significantly above chance levels. The **EmoEEG-MC dataset** serves as a foundational resource for advancing cross-context emotion recognition and enhancing the real-world application of emotion decoding methods.\r\n\r\n## Dataset Description\r\n\r\nThe dataset includes EEG data from 60 participants, along with peripheral physiological data (PPG and GSR) for some participants. Among the 60 participants, **sub01-sub54** have complete trials (21 imagery trials and 21 video trials), while **sub55-sub60** have missing trials. The details of the missing trials are as follows:\r\n\r\n- **sub55**: Missing 3 imagery trials (Trials 19-21) and 3 video trials (Trials 40-42).\r\n- **sub56**: Missing 2 imagery trials (Trials 20 and 21).\r\n- **sub57**: Missing 4 imagery trials (Trials 6, 8, 13, and 21) and 6 video trials (Trials 23, 24, 36, 37, 38, and 42).\r\n- **sub58**: Missing 3 imagery trials (Trials 9, 20, and 21).\r\n- **sub59**: Missing 6 imagery trials (Trials 2, 4, 6, 12, 19, and 21) and 4 video trials (Trials 29, 37, 39, and 42).\r\n- **sub60**: Missing 14 imagery trials (Trials 8-21) and 12 video trials (Trials 31-42).\r\n\r\nAll missing values are denoted as **n/a** in the participants' behavioral data.\r\n\r\n## Experimental Trial Reordering and Missing Trial Information\r\n\r\n### Trial Reordering\r\n\r\nAfter reordering, the sequence for both imagery and video trials is as follows:\r\n\r\n`reorder = ['sad4', 'sad5', 'sad8', 'dis4', 'dis5', 'dis8', 'fear4', 'fear5', 'fear8', 'neu4', 'neu5', 'neu8', 'joy4', 'joy5', 'joy8', 'ten4', 'ten5', 'ten8', 'ins4', 'ins5', 'ins8']`\r\n\r\n### Full Trial Participants\r\n\r\nFor participants with complete trials (**sub01-sub54**, with the same order for both imagery and video trials; detailed stimulus information can be found in `sub-xx/sub-xx_events`), the experimental sequence is as follows:\r\n\r\n1. `['joy5', 'ins5', 'joy8', 'fear8', 'sad8', 'dis5', 'neu4', 'neu5', 'neu8', 'ten5', 'ten8', 'joy4', 'dis4', 'fear4', 'sad4', 'ins8', 'ins4', 'ten4', 'dis8', 'fear5', 'sad5']`\r\n2. `['fear8', 'fear5', 'dis4', 'ins8', 'joy8', 'ins4', 'neu4', 'neu8', 'neu5', 'sad4', 'dis8', 'fear4', 'ten5', 'ten8', 'joy4', 'dis5', 'sad8', 'sad5', 'joy5', 'ten4', 'ins5']`\r\n3. `['ten4', 'joy4', 'joy8', 'neu4', 'neu8', 'neu5', 'dis5', 'fear4', 'fear5', 'ten8', 'ten5', 'ins5', 'fear8', 'dis4', 'dis8', 'ins8', 'joy5', 'ins4', 'sad4', 'sad5', 'sad8']`\r\n4. `['fear5', 'dis8', 'dis5', 'joy4', 'ten5', 'ins5', 'neu4', 'neu8', 'neu5', 'sad8', 'fear8', 'sad4', 'ins4', 'ins8', 'joy8', 'fear4', 'sad5', 'dis4', 'ten4', 'joy5', 'ten8']`\r\n5. `['joy8', 'ten4', 'ins5', 'fear5', 'sad5', 'dis4', 'neu4', 'neu5', 'neu8', 'joy4', 'ten8', 'joy5', 'sad4', 'dis8', 'fear8', 'ins4', 'ten5', 'ins8', 'sad8', 'dis5', 'fear4']`\r\n6. `['joy8', 'ins5', 'ins8', 'dis4', 'dis8', 'fear8', 'ten4', 'joy5', 'ten5', 'dis5', 'fear5', 'fear4', 'ten8', 'ins4', 'joy4', 'sad8', 'sad4', 'sad5', 'neu4', 'neu5', 'neu8']`\r\n7. `['joy8', 'ten8', 'joy4', 'fear4', 'sad5', 'dis5', 'ins5', 'ten5', 'ten4', 'dis4', 'sad8', 'dis8', 'ins4', 'ins8', 'joy5', 'sad4', 'fear8', 'fear5', 'neu4', 'neu5', 'neu8']`\r\n8. `['neu4', 'neu5', 'neu8', 'dis8', 'sad4', 'fear5', 'ins4', 'ins5', 'ten5', 'dis4', 'sad8', 'fear4', 'ins8', 'joy4', 'ten8', 'fear8', 'dis5', 'sad5', 'ten4', 'joy8', 'joy5']`\r\n9. `['sad5', 'fear4', 'fear8', 'joy4', 'joy8', 'ten5', 'dis8', 'dis5', 'sad4', 'neu4', 'neu8', 'neu5', 'ins8', 'ten8', 'ins4', 'sad8', 'fear5', 'dis4', 'joy5', 'ten4', 'ins5']`\r\n10. `['sad4', 'fear5', 'sad8', 'joy8', 'ten8', 'joy4', 'sad5', 'dis8', 'fear4', 'neu4', 'neu8', 'neu5', 'ten4', 'ten5', 'ins4', 'dis4', 'fear8', 'dis5', 'joy5', 'ins5', 'ins8']`\r\n11. `['joy4', 'ins4', 'joy5', 'fear8', 'dis8', 'sad4', 'ten8', 'ins5', 'ten5', 'sad5', 'sad8', 'fear5', 'ins8', 'ten4', 'joy8', 'neu8', 'neu4', 'neu5', 'fear4', 'dis4', 'dis5']`\r\n12. `['sad8', 'fear5', 'fear8', 'ten8', 'ten5', 'joy8', 'fear4', 'sad4', 'sad5', 'neu4', 'neu8', 'neu5', 'ins8', 'ins4', 'ten4', 'dis5', 'dis8', 'dis4', 'joy5', 'joy4', 'ins5']`\r\n13. `['sad8', 'dis8', 'sad4', 'ten4', 'ten8', 'ins4', 'dis5', 'fear8', 'sad5', 'ten5', 'ins5', 'joy8', 'neu4', 'neu8', 'neu5', 'fear5', 'fear4', 'dis4', 'joy4', 'joy5', 'ins8']`\r\n14. `['ins8', 'ten4', 'ins5', 'neu4', 'neu8', 'neu5', 'sad5', 'dis4', 'sad4', 'ins4', 'ten8', 'ten5', 'dis8', 'sad8', 'fear8', 'joy5', 'joy4', 'joy8', 'fear4', 'fear5', 'dis5']`\r\n15. `['ins8', 'ten5', 'ten8', 'sad8', 'sad4', 'sad5', 'joy4', 'ins4', 'ins5', 'fear8', 'fear5', 'fear4', 'ten4', 'joy5', 'joy8', 'neu5', 'neu4', 'neu8', 'dis4', 'dis5', 'dis8']`\r\n16. `['fear4', 'dis4', 'fear8', 'ins8', 'joy8', 'ten8', 'dis5', 'sad4', 'dis8', 'ins5', 'ins4', 'joy4', 'neu8', 'neu4', 'neu5', 'fear5', 'sad8', 'sad5', 'joy5', 'ten5', 'ten4']`\r\n17. `['ten5', 'ins4', 'ins8', 'dis8', 'fear4', 'sad5', 'ins5', 'joy8', 'ten4', 'sad8', 'fear8', 'fear5', 'ten8', 'joy5', 'joy4', 'sad4', 'dis5', 'dis4', 'neu5', 'neu4', 'neu8']`\r\n18. `['neu4', 'neu5', 'neu8', 'sad4', 'dis8', 'dis5', 'joy4', 'ten4', 'ten5', 'sad5', 'fear5', 'fear4', 'ins5', 'ins4', 'ten8', 'dis4', 'fear8', 'sad8', 'joy8', 'ins8', 'joy5']`\r\n19. `['joy5', 'ten8', 'ins4', 'fear4', 'dis8', 'sad4', 'ten5', 'joy8', 'joy4', 'sad8', 'dis5', 'fear8', 'neu8', 'neu4', 'neu5', 'ins5', 'ten4', 'ins8', 'fear5', 'dis4', 'sad5']`\r\n20. `['joy5', 'ins8', 'joy4', 'neu4', 'neu5', 'neu8', 'fear4', 'sad4', 'fear8', 'ins5', 'ten4', 'ten5', 'dis4', 'sad8', 'sad5', 'ten8', 'ins4', 'joy8', 'dis5', 'fear5', 'dis8']`\r\n21. `['ten8', 'joy4', 'ins5', 'sad4', 'dis4', 'fear8', 'ins8', 'joy8', 'ins4', 'neu8', 'neu4', 'neu5', 'sad5', 'sad8', 'fear5', 'ten5', 'joy5', 'ten4', 'fear4', 'dis5', 'dis8']`\r\n22. `['joy5', 'ten8', 'ten4', 'dis4', 'fear4', 'fear5', 'joy8', 'ten5', 'joy4', 'sad5', 'sad8', 'dis8', 'neu5', 'neu8', 'neu4', 'ins4', 'ins5', 'ins8', 'fear8', 'sad4', 'dis5']`\r\n23. `['neu4', 'neu5', 'neu8', 'dis4', 'fear4', 'sad8', 'ins8', 'joy4', 'ten8', 'fear8', 'fear5', 'sad5', 'ten4', 'in","bids_version":"1.6.0","sessions_count":2,"publish_date":null,"embedding_dirty":0,"license_tier":"public","zarr_status":"ready","zarr_converted_at":"2026-08-27 01:30:15","zarr_store_count":96,"zarr_index_etag":"b2f208d253d99864e7f8205ff91ce457","zarr_source_commit":"6ba813ea30952681a23badd5a8645c0560304330","archive_status":"ready","archive_size":41172890322,"archive_retry_count":0,"records_status":"ready","archive_skip_reason":null,"zarr_errors":7,"zarr_failure_count":5,"zarr_deterministic":0,"zarr_failed_at":"2026-08-27 01:30:15","num_dataset_citations":3,"num_datapaper_citations":0,"n_channels":64,"electrode_system":null,"has_hed":0,"hed_version":null,"is_exemplar":0,"bytes_present":75593676532,"data_complete":1,"withdrawn_at":null,"withdrawn_reason":null,"archive_complete":null,"archive_absent_files":null,"archive_declared_files":null,"zarr_pool_breaks":0,"total_recording_duration":574999,"recording_duration_min":348,"recording_duration_max":17598,"recording_count":101,"recordings_unavailable":5,"recordings_measured":96,"channel_count_min":64,"channel_count_max":64,"sampling_frequency":1200,"power_line_frequency":50,"eeg_reference":"common","placement_scheme":"10-20 system","sweep_stamps":"{\"enrichment_updated_at\":\"2026-08-19 01:31:21\",\"metadata_updated_at\":\"2026-08-19 01:31:41\",\"archive_checked_at\":\"2026-06-27 09:11:26\",\"zarr_checked_at\":null,\"records_checked_at\":\"2026-06-27 08:53:42\",\"citations_updated_at\":\"2026-09-08 03:00:51\",\"channel_montage_checked_at\":\"2026-06-28 23:48:09\",\"hed_checked_at\":\"2026-06-30 05:21:18\",\"data_checked_at\":\"2026-08-22 03:00:38\",\"availability_report_at\":\"2026-07-23 01:25:36\",\"recording_stats_at\":\"2026-09-02 11:33:25\",\"signal_defaults_at\":\"2026-09-02 12:38:00\"}","participants":60,"num_citations":3,"latest_version":"v1.0.0","zarr_verify_status":null,"zarr_verified_at":null,"owner_username":"nemarAdmin","owner_github":"nemarAdmin","file_size_formatted":"70.40 GB","zarr_data_failures":{"count":5,"detail_ref":"zarr/index.json","compacted_by":"migration_0074"},"zarr_index_url":"https://zarr.nemar.org/on005540/zarr/index.json","attestation_deposit_type":null,"attestation_key_status":null,"attestation_deidentified":null,"attestation_no_duplicate":null,"attestation_upstream_source":null,"attestation_accepted_at":null}}