{"status":"OK","data":{"id":485635,"identifier":"A0NLTQ","persistentUrl":"https://doi.org/10.34894/A0NLTQ","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2025-07-09","storageIdentifier":"surf://10.34894/A0NLTQ","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9997,"datasetType":"dataset","locks":[],"latestVersion":{"id":30678,"datasetId":485635,"datasetPersistentId":"doi:10.34894/A0NLTQ","datasetType":"dataset","storageIdentifier":"surf://10.34894/A0NLTQ","versionNumber":1,"internalVersionNumber":38,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","lastUpdateTime":"2025-07-09T10:10:10Z","releaseTime":"2025-07-09T10:10:10Z","createTime":"2025-06-06T12:54:50Z","publicationDate":"2025-07-09","citationDate":"2025-07-09","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9997,"license":{"name":"CC-BY-NC-4.0","uri":"http://creativecommons.org/licenses/by-nc/4.0","iconUri":"https://i.creativecommons.org/l/by-nc/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"MCSD 1.0 - Multimodal Chinese Sarcasm Dataset"},{"typeName":"alternativeTitle","multiple":true,"typeClass":"primitive","value":["MCSD"]},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Gao, Xiyuan"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-0870-6721"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Bruce Xiao Wang"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/0030zas98"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-3564-2911"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Meiling Zhang"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Shuming Huang"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/0030zas98"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Zhu Li"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-1409-2482"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Shekhar Nayak"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-4277-4851"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Matt Coler"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"https://ror.org/012p63287","expandedvalue":{"scheme":"http://www.grid.ac/ontology/","termName":"University of Groningen","@type":"https://schema.org/Organization"}},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-1409-2482"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Groningen Digital Competence Centre"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"rug.nl"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"This repository includes full text file of Multimodal Chinese Sarcasm Dataset (MCSD), a curated dataset for research on multimodal sarcasm detection in Mandarin Chinese publicly broadcasted stand-up comedy. The corpus is structured as follows:<br><br>\n<ul>\n<li>unique utterance ID for each transcribed segment.</li>\n<li>manually verified transcription of the spoken utterance (in Mandarin).</li>\n<li>pseudonymized speaker ID.</li>\n<li>annotated label (sarcastic / not sarcastic) for each transcription.</li>\n<li>aligned start and end timestamps.</li>\n<li>reference to the original publicly available video.</li>\n</ul>\nFor full <em>dataset description and annotation guidelines</em>, please see: <a href=\"https://github.com/x-y-g/MCSD/wiki\">Link</a><br><br>\n\n<h4>Contributors and roles</h4>\n<ul>\n<li>Xiyuan Gao (University of Groningen) – PhD researcher. Responsible for dataset design, transcription processing, annotation guideline.</li>\n<li>Dr. Bruce Xiao Wang (Hong Kong Polytechnic University) – Collaborator and linguistic expert. Contributed to the research framework, research methodology design, and Mandarin discourse insights.</li>\n<li>Meiling Zhang, Shuming Zhang, and Zhu Li – Carried out manual labeling of sarcasm in the transcribed data based on developed annotation protocols.</li>\n<li>Dr. Matt Coler & Dr. Shekhar Nayak (University of Groningen) – Supervisors. Provided research supervision and guidance on ethical compliance.</li>"},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2025-07-02"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities","Computer and Information Science"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"multimodal sarcasm detection, Mandarin Chinese, tonal language, prosody, humor detection, speech analysis, sentiment analysis, pragmatics, spoken language processing, cross-lingual NLP, annotated speech corpus, paralinguistic features, computational linguistics, benchmark sarcasm dataset"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Sarcasm and irony, homor"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"X. Gao, B. X. Wang, M. Zhang, S. Huang, Z. Li, S. Nayak, and M. Coler, “A Multimodal Chinese Dataset for Cross-lingual Sarcasm Detection,” in Proc. Interspeech 2025, Rotterdam, The Netherlands, Aug. 17–21, 2025 (in press)."}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"<h4>Dataset highlights:</h4>\n<ul>\n<li><strong>Multimodality</strong>: This is a novel <em>multimodal sarcasm dataset in Mandarin Chinese</em>, offering resources for cross-lingual sarcasm detection research.</li>\n  <li><strong>Linguistically grounded annotation</strong>: The annotation protocol is informed by discourse theory and sarcasm typology, <em>balance sarcasm’s inherent ambiguity with annotator variability in interpretation</em>.</li>\n  <li><strong>Reproducibility-focused design</strong>: The dataset was built using a standardized pipeline for <em>data collection, processing, and annotation</em>, enabling reliable replication. To use the pipeline, please refer to the <a href=\"https://github.com/x-y-g/MCSD/wiki\">Github repo</a></li>\n</ul>"},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["Chinese"]},{"typeName":"distributor","multiple":true,"typeClass":"compound","value":[{"distributorName":{"typeName":"distributorName","multiple":false,"typeClass":"primitive","value":"DataverseNL Network"},"distributorAffiliation":{"typeName":"distributorAffiliation","multiple":false,"typeClass":"primitive","value":"DANS"},"distributorAbbreviation":{"typeName":"distributorAbbreviation","multiple":false,"typeClass":"primitive","value":"DVNL"},"distributorURL":{"typeName":"distributorURL","multiple":false,"typeClass":"primitive","value":"https://dataverse.nl/"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Silva Correia Alves, Ana"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2025-06-06"},{"typeName":"timePeriodCovered","multiple":true,"typeClass":"compound","value":[{"timePeriodCoveredStart":{"typeName":"timePeriodCoveredStart","multiple":false,"typeClass":"primitive","value":"2017-08-11"},"timePeriodCoveredEnd":{"typeName":"timePeriodCoveredEnd","multiple":false,"typeClass":"primitive","value":"2024-10-23"}}]},{"typeName":"dateOfCollection","multiple":true,"typeClass":"compound","value":[{"dateOfCollectionStart":{"typeName":"dateOfCollectionStart","multiple":false,"typeClass":"primitive","value":"2025-10-01"},"dateOfCollectionEnd":{"typeName":"dateOfCollectionEnd","multiple":false,"typeClass":"primitive","value":"2025-02-01"}}]},{"typeName":"dataSources","multiple":true,"typeClass":"primitive","value":["The program's official channel on YouTube"]},{"typeName":"accessToSources","multiple":false,"typeClass":"primitive","value":"<a href=\"https://developers.google.com/youtube/v3\">YouTube Data API</a>"}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/A0NLTQ"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:a2778b91-1653-40cd-98fc-96c2f7b62d27"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-4cfdb3b1-307f-4f31-b141-946016f70496"}]}},"files":[{"description":"This ZIP archive contains a snapshot of the GitHub repository for the dataset (V1). It includes dataset documentation, annotation guidelines, and metadata files as hosted on GitHub at the time of public release.","label":"MCSD-v1-GithubSnapshot.zip","restricted":false,"version":3,"datasetVersionId":30678,"dataFile":{"id":488777,"persistentId":"","filename":"MCSD-v1-GithubSnapshot.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":16927332,"description":"This ZIP archive contains a snapshot of the GitHub repository for the dataset (V1). It includes dataset documentation, annotation guidelines, and metadata files as hosted on GitHub at the time of public release.","storageIdentifier":"surf://store:197cccb2924-909aae776ba8","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"fd075bad7f7dfcd009c14f5e74ae0e4be977fdfe"},"tabularData":false,"creationDate":"2025-07-02","publicationDate":"2025-07-09","lastUpdateTime":"2025-07-09T10:10:10Z","fileAccessRequest":true}},{"description":"A table containing 2705 manually verified transcriptions of utterances, sarcasm labels (sarcasm, non-sarcasm), pseudonymized speaker IDs, gender, and timestamps indicating the segment boundaries within the publicly available source video.","label":"MCSD_v1.xlsx","restricted":false,"version":1,"datasetVersionId":30678,"dataFile":{"id":486776,"persistentId":"","filename":"MCSD_v1.xlsx","contentType":"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet","friendlyType":"MS Excel Spreadsheet","filesize":375499,"description":"A table containing 2705 manually verified transcriptions of utterances, sarcasm labels (sarcasm, non-sarcasm), pseudonymized speaker IDs, gender, and timestamps indicating the segment boundaries within the publicly available source video.","storageIdentifier":"surf://store:1977cd9a25e-f0d249c3a7a1","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"8a4491cca46df4c767b0feb104755628442bbd09"},"tabularData":false,"creationDate":"2025-06-17","publicationDate":"2025-07-09","lastUpdateTime":"2025-07-09T10:10:10Z","fileAccessRequest":true}},{"description":"A table mapping each item to its corresponding publicly available video URL. To guarantee reproducibility and transparency source referencing, each item matches the item field in transcripts_v1.csv.","label":"metadata_v1.xlsx","restricted":false,"version":1,"datasetVersionId":30678,"dataFile":{"id":486775,"persistentId":"","filename":"metadata_v1.xlsx","contentType":"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet","friendlyType":"MS Excel Spreadsheet","filesize":6654,"description":"A table mapping each item to its corresponding publicly available video URL. To guarantee reproducibility and transparency source referencing, each item matches the item field in transcripts_v1.csv.","storageIdentifier":"surf://store:1977cd9a1b1-1fd8c66d71d5","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"213dc9cce5b3c02406804aae6c0f846430821ade"},"tabularData":false,"creationDate":"2025-06-17","publicationDate":"2025-07-09","lastUpdateTime":"2025-07-09T10:10:10Z","fileAccessRequest":true}}]}}}