{"id":4081426,"identifier":"DVN/BAKGET","persistentUrl":"https://doi.org/10.7910/DVN/BAKGET","protocol":"doi","authority":"10.7910","separator":"/","publisher":"Harvard Dataverse","publicationDate":"2021-09-01","storageIdentifier":"s3://10.7910/DVN/BAKGET","datasetType":"dataset","datasetVersion":{"id":609165,"datasetId":4081426,"datasetPersistentId":"doi:10.7910/DVN/BAKGET","datasetType":"dataset","storageIdentifier":"s3://10.7910/DVN/BAKGET","versionNumber":6,"internalVersionNumber":8,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","distributionDate":"2026-01-10","productionDate":"2026-01-10","UNF":"UNF:6:5aIjqRFvBBIPqxGQtNC/aA==","lastUpdateTime":"2026-01-10T19:37:35Z","releaseTime":"2026-01-10T19:37:35Z","createTime":"2026-01-10T19:29:37Z","publicationDate":"2021-09-01","citationDate":"2021-09-01","termsOfUse":"Creative Commons Attribution-ShareAlike 4.0 International Public License (CC BY-SA 4.0)","conditions":"https://creativecommons.org/licenses/by-sa/4.0/","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Chinese Ministry of Foreign Affairs Press Conferences Corpus (CMFA PressCon)"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Mochtak, Michal"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Radboud University"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0001-5598-5642"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Turcsanyi, Richard Q."},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Palacky University Olomouc"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-2036-6029"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Mochtak, Michal"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Radboud University"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"mochtak@gmail.com"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"The repository contains an original corpus of the Chinese Ministry of Foreign Affairs Press Conferences (CMFA PresCon) mapping two decades of Chinese diplomatic discourse and priorities in China’s foreign policy. The dataset is organized around a question/response structure extracted from the official transcripts of press conferences held between 15 October 2002 and 31 December 2025 and in its current version (v6) counts 35 346 data points."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2026-01-10"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science","Social Sciences"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"corpus"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"China"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"foreign affairs"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"text as data"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"discourse"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"international relations"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"political science"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"natural language processing"}},{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"quantitative text analysis"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"When using the CMFA PressCon data, please cite:\nMochtak, Michal and Richard Q. Turcsanyi (2021): \"Studying Chinese Foreign Policy Narratives: Introducing the Ministry of Foreign Affairs Press Conferences Corpus\". <i>Journal of Chinese Political Science</i>, 26 (4): 743-761."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.1007/s11366-021-09762-3"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://link.springer.com/article/10.1007/s11366-021-09762-3"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"Unfortunately, we were not able to check all 35 346 question/answers dyads manually, so there is no guarantee that the dataset is without any errors. As we plan to maintain/update the dataset further, feel free to contact us if you spot anything problematic or something that needs to be fixed systematically. We will include the changes in the next release.\n<br><br>\nImportant: From version 6 of the dataset onward, we no longer publish linguistic annotations. There is not enough interest in them to justify the additional effort required to create and maintain the extra data."},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2026-01-10"},{"typeName":"distributionDate","multiple":false,"typeClass":"primitive","value":"2026-01-10"},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Mochtak, Michal"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2026-01-10"},{"typeName":"timePeriodCovered","multiple":true,"typeClass":"compound","value":[{"timePeriodCoveredStart":{"typeName":"timePeriodCoveredStart","multiple":false,"typeClass":"primitive","value":"2002-10-15"},"timePeriodCoveredEnd":{"typeName":"timePeriodCoveredEnd","multiple":false,"typeClass":"primitive","value":"2025-12-31"}}]},{"typeName":"dataSources","multiple":true,"typeClass":"primitive","value":["Chinese Ministry of Foreign Affairs (https://www.fmprc.gov.cn/mfa_eng/)\nWayback Machine (http://web.archive.org/)"]}]}},"files":[{"label":"changelog.txt","restricted":false,"version":1,"datasetVersionId":609165,"dataFile":{"id":13349338,"persistentId":"","filename":"changelog.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":4962,"storageIdentifier":"s3://dvn-cloud:19ba96353be-1cb4c26aeeb0","rootDataFileId":-1,"md5":"368d7ac8d996b495c64b519b6489ffe5","checksum":{"type":"MD5","value":"368d7ac8d996b495c64b519b6489ffe5"},"tabularData":false,"creationDate":"2026-01-10","publicationDate":"2026-01-10","lastUpdateTime":"2026-01-10T19:37:35Z","fileAccessRequest":false}},{"description":"Full dataset; v6","label":"CMFA_PressCon_v6.xlsx","restricted":false,"version":1,"datasetVersionId":609165,"dataFile":{"id":13349339,"persistentId":"","filename":"CMFA_PressCon_v6.xlsx","contentType":"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet","friendlyType":"MS Excel Spreadsheet","filesize":22842450,"description":"Full dataset; v6","storageIdentifier":"s3://dvn-cloud:19ba9635550-ddcf5fd8d28b","rootDataFileId":-1,"md5":"fa4e7643af7aa80fc0c2b85a64b9d410","checksum":{"type":"MD5","value":"fa4e7643af7aa80fc0c2b85a64b9d410"},"tabularData":false,"creationDate":"2026-01-10","publicationDate":"2026-01-10","lastUpdateTime":"2026-01-10T19:37:35Z","fileAccessRequest":false}},{"label":"CODEBOOK_CMFA_PressCon_v6.pdf","restricted":false,"version":1,"datasetVersionId":609165,"dataFile":{"id":13349337,"persistentId":"","filename":"CODEBOOK_CMFA_PressCon_v6.pdf","contentType":"application/pdf","friendlyType":"Adobe PDF","filesize":148409,"storageIdentifier":"s3://dvn-cloud:19ba963639d-f7faf9772c7a","rootDataFileId":-1,"md5":"e87ed79568f62e1f71f1cc98155eb36e","checksum":{"type":"MD5","value":"e87ed79568f62e1f71f1cc98155eb36e"},"tabularData":false,"creationDate":"2026-01-10","publicationDate":"2026-01-10","lastUpdateTime":"2026-01-10T19:37:35Z","fileAccessRequest":false}},{"label":"readme.txt","restricted":false,"version":1,"datasetVersionId":609165,"dataFile":{"id":13349336,"persistentId":"","filename":"readme.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":784,"storageIdentifier":"s3://dvn-cloud:19ba963568b-5243a56357a6","rootDataFileId":-1,"md5":"4a3dfe628923e590d9043e237fac7c9c","checksum":{"type":"MD5","value":"4a3dfe628923e590d9043e237fac7c9c"},"tabularData":false,"creationDate":"2026-01-10","publicationDate":"2026-01-10","lastUpdateTime":"2026-01-10T19:37:35Z","fileAccessRequest":false}}],"citation":"Mochtak, Michal; Turcsanyi, Richard Q., 2021, \"Chinese Ministry of Foreign Affairs Press Conferences Corpus (CMFA PressCon)\", https://doi.org/10.7910/DVN/BAKGET, Harvard Dataverse, V6, UNF:6:5aIjqRFvBBIPqxGQtNC/aA== [fileUNF]"}}