{"status":"OK","data":{"id":20392,"identifier":"dans-xgp-nyp7","persistentUrl":"https://doi.org/10.17026/DANS-XGP-NYP7","protocol":"doi","authority":"10.17026","separator":"/","publisher":"DANS Data Station Social Sciences and Humanities","publicationDate":"2021-01-12","storageIdentifier":"surf://10.17026/dans-xgp-nyp7","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9988,"datasetType":"dataset","locks":[],"latestVersion":{"id":30066,"datasetId":20392,"datasetPersistentId":"doi:10.17026/DANS-XGP-NYP7","datasetType":"dataset","storageIdentifier":"surf://10.17026/dans-xgp-nyp7","versionNumber":1,"internalVersionNumber":8,"versionMinorNumber":1,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","distributionDate":"2021-01-05","productionDate":"2021-01-04","lastUpdateTime":"2026-07-19T13:42:55Z","releaseTime":"2026-07-19T13:42:55Z","createTime":"2026-07-19T13:39:02Z","publicationDate":"2021-01-12","citationDate":"2021-01-12","versionNote":"The Python package langdetect was used to semi-automatically identify the languages used in the metadata. Human curators verified and corrected the results. If you notice any inaccuracies, please contact DANS.","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9988,"license":{"name":"CC-BY-4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://licensebuttons.net/l/by/4.0/88x31.png"},"termsOfAccess":"","fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Evaluating MT for LIWC"},{"typeName":"otherId","multiple":true,"typeClass":"compound","value":[{"otherIdAgency":{"typeName":"otherIdAgency","multiple":false,"typeClass":"primitive","value":"DANS-KNAW"},"otherIdValue":{"typeName":"otherIdValue","multiple":false,"typeClass":"primitive","value":"easy-dataset:197027"}}]},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"P Boot"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Huygens ING"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-7399-3539"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"P  Boot"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Huygens ING"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"<p>Data belonging to article 'Machine-translated texts as an alternative to translated dictionaries for LIWC'.</p><p>The data are the result of computations described in the article. Each zip file contains the results of a single run. The name of the zip file consists of the run number, the language code, the corpus used, the MT engine used and the LIWC version.</p><p>The zip files contain:<br>- the LIWC output for the working language, English gold translation and English machine translation (.csv files).<br>- computed statistics, including correlations and effect sizes for each of the three language pairs (.csv files)<br>- graphs giving the correlations and effect sizes for each LIWC category as well as the relevant averages (.png files)<br>- a report showing a number of texts where there are sizable differences between the LIWC output in the different languages (.html files)<br>- the scripts used in performing the computations</p>"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"LIWC"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"machine translation"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2021-01-04"},{"typeName":"distributionDate","multiple":false,"typeClass":"primitive","value":"2021-01-05"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2021-01-05"}]},"dansRights":{"displayName":"Rights Metadata","name":"dansRights","fields":[{"typeName":"dansRightsHolder","multiple":true,"typeClass":"primitive","value":["dr P Boot (Huygens ING)","dr P Boot (Huygens ING)"]},{"typeName":"dansPersonalDataPresent","multiple":false,"typeClass":"controlledVocabulary","value":"Unknown"},{"typeName":"dansMetadataLanguage","multiple":true,"typeClass":"controlledVocabulary","value":["English"]}]},"dansRelationMetadata":{"displayName":"Relation Metadata","name":"dansRelationMetadata","fields":[{"typeName":"dansAudience","multiple":true,"typeClass":"primitive","value":["https://www.narcis.nl/classification/D30100"],"expandedvalue":[{"@id":"https://www.narcis.nl/classification/D30100","termName":[{"lang":"nl","value":"Digital humanities"},{"lang":"en","value":"Digital humanities"}],"vocabularyUri":"https://www.narcis.nl/classification/"}]}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.17026/DANS-XGP-NYP7"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.1"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:d2633578-6fe0-42b3-84a5-38ba1e96593e"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-1y-jn9e"}]}},"files":[{"description":"","label":"01 nl dpc joshua 2007.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20401,"persistentId":"","filename":"01 nl dpc joshua 2007.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":1722897,"description":"","storageIdentifier":"surf://store:186dfdcd938-40c3b9863fb1","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"e53e76e411aaaa93a137d6cc0b86f3cdb01dd987"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"02 nl dpc joshua 2015.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20407,"persistentId":"","filename":"02 nl dpc joshua 2015.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":3752329,"description":"","storageIdentifier":"surf://store:186dfdcdf86-b6f6e76e8504","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"ad54e5a47dd7c70e7f552e07112950beafe31777"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"03 nl ted gnmt 2007.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20396,"persistentId":"","filename":"03 nl ted gnmt 2007.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2884240,"description":"","storageIdentifier":"surf://store:186dfdcd39e-ea7c1d5adb57","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"d4f2eebbb7c6a4ed9fac07db4035025ba1206df9"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"04 nl ted gpbmt 2007.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20397,"persistentId":"","filename":"04 nl ted gpbmt 2007.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":1468403,"description":"","storageIdentifier":"surf://store:186dfdcd534-ea8586fc8198","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"c7c80b3a2fc382e9f928cf2823d588b67579040f"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"05 nl ted joshua 2007.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20406,"persistentId":"","filename":"05 nl ted joshua 2007.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2120064,"description":"","storageIdentifier":"surf://store:186dfdcde1b-317dcf6d56ed","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"30609b0bfec515eb824bc884bdd6c05fbef7eb50"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"06 nl ted joshua 2015.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20402,"persistentId":"","filename":"06 nl ted joshua 2015.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":1802387,"description":"","storageIdentifier":"surf://store:186dfdcda8e-1498ed2c66e5","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"73c37c504206a3d675088aa2d0843d97f3ab3859"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"07 de ted joshua 2001.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20400,"persistentId":"","filename":"07 de ted joshua 2001.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2823438,"description":"","storageIdentifier":"surf://store:186dfdcd7da-da0c99b8c98e","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"ef1677ce0575a56639ad1d3a2f86218524134f7e"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"08 de ted joshua 2015.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20395,"persistentId":"","filename":"08 de ted joshua 2015.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2087076,"description":"","storageIdentifier":"surf://store:186dfdcd272-507a2c6a9f81","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"01a3ebccd005a691936caa8e8c030b1950cbd512"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"09 de ted fairseq 2001.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20404,"persistentId":"","filename":"09 de ted fairseq 2001.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2138610,"description":"","storageIdentifier":"surf://store:186dfdcdbbc-4ac155ddc334","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"5b89faba255e76f6350ff7e6dd58003892cdf269"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"10 de ted fairseq 2015.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20399,"persistentId":"","filename":"10 de ted fairseq 2015.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2437888,"description":"","storageIdentifier":"surf://store:186dfdcd69e-9882c54d1309","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"0e202a5a4d7f135abde3c0cbe9907cb6310b851a"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"11 es ted joshua 2007.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20405,"persistentId":"","filename":"11 es ted joshua 2007.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":2125010,"description":"","storageIdentifier":"surf://store:186dfdcdce2-5ebf8b17dc6c","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"8ecf5663f2f1ee4f68661419260619b716fe54a7"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}},{"description":"","label":"easy-migration.zip","restricted":false,"version":1,"datasetVersionId":30066,"dataFile":{"id":20394,"persistentId":"","filename":"easy-migration.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":17324,"description":"","storageIdentifier":"surf://store:186dfdcd197-0beac539fadf","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"465c97366794c940205d8cbe87590ada6d846ffc"},"tabularData":false,"creationDate":"2023-03-14","publicationDate":"2021-01-12","lastUpdateTime":"2026-07-19T13:42:55Z","fileAccessRequest":true}}]}}}