{"status":"OK","data":{"id":138798,"identifier":"XXXSXJ","persistentUrl":"https://doi.org/10.34894/XXXSXJ","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2026-03-10","storageIdentifier":"surf://10.34894/XXXSXJ","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9992,"datasetType":"dataset","locks":[],"latestVersion":{"id":3917,"datasetId":138798,"datasetPersistentId":"doi:10.34894/XXXSXJ","datasetType":"dataset","storageIdentifier":"surf://10.34894/XXXSXJ","versionNumber":1,"internalVersionNumber":32,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","lastUpdateTime":"2026-03-10T13:42:29Z","releaseTime":"2026-03-10T13:42:29Z","createTime":"2021-09-02T12:32:28Z","publicationDate":"2026-03-10","citationDate":"2026-03-10","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9992,"license":{"name":"CC-BY-4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://i.creativecommons.org/l/by/4.0/88x31.png"},"fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Measuring the Response Quality of Online Open-Ended Questions in Linguistics Complexity"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Xu, Xiao"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-2325-8306"}}]},{"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":"University of Groningen"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"Here you may find the code and data used in the paper \"Measuring the Response Quality of Online Open-Ended Questions in Linguistics Complexity\" (Xu et al. 2026).\n\n<br/>\nOpen-ended questions (OEQs) are important survey tools for social scientists, but their response quality is often disputed due to the additional load they impose on the respondent. To find ideally worded questions and survey strategies that encourage high-quality responses to OEQs, the quality of textual responses is often assessed. Response length and response latency are often used as measures of response quality, but they do not provide enough information on interpretability and richness of the responses. In this study, we propose a novel way of evaluating the data quality of open-ended responses by leveraging approaches from Natural Language Processing (NLP), measuring different linguistic complexity features of responses. Using various automatically generated linguistic features, we compared the quality of responses to distinctly worded sets of questions related to people’s uncertainty about their intention of having children. Overall, we found that the different wording of questions may affect responses on different aspects of linguistic complexity, which canonical indicators fail to reveal. In addition, we found that the variance in response quality could be attributed to both respondent characteristics and different versions of questions. These findings offer practical strategies for incorporating OEQs into a large-scale demographic survey, as well as providing a new perspective in evaluating responses to OEQs in future surveys."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2026"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Social Sciences"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"open-ended question"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"online survey"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"CAWI"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"response quality"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"natural language processing"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["Dutch","English"]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Elsenga, Christina"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2021-09-02"},{"typeName":"relatedMaterial","multiple":true,"typeClass":"primitive","value":["Xu, X., Gauthier, A., Stulp, G., & van den Bosch, A. (2025). Understanding narratives of uncertainty in fertility intentions of Dutch women: A neural topic modeling approach. Social Science Computer Review, 43(4), 727-749.\ndoi 10.1177/08944393241269406"]}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/XXXSXJ"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:0806315e-f4cf-4a55-b290-2c747e2224c3"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-414e02ce-c940-4e7e-850b-880944aa59c1"}]}},"files":[{"description":"The Python script used to generate dataset that combines original data and t-scan features (L_Kinderwens_2021_tscan.csv).","label":"generate.ipynb","restricted":false,"version":2,"datasetVersionId":3917,"dataFile":{"id":216335,"persistentId":"","filename":"generate.ipynb","contentType":"application/x-ipynb+json","friendlyType":"Jupyter Notebook","filesize":110607,"description":"The Python script used to generate dataset that combines original data and t-scan features (L_Kinderwens_2021_tscan.csv).","storageIdentifier":"surf://store:17dda1a6245-b7c36424117d","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"b125a5e3ac86c3d3420c808d45a8bf4cf00fe79b"},"tabularData":false,"creationDate":"2021-12-21","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"description":"Data file containing features generated with t-scan, with original responses and personal information removed. For full data, please refer to https://www.lissdata.nl/","label":"L_Kinderwens_2021_cleaned.csv","restricted":false,"version":2,"datasetVersionId":3917,"dataFile":{"id":200175,"persistentId":"","filename":"L_Kinderwens_2021_cleaned.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":48601,"description":"Data file containing features generated with t-scan, with original responses and personal information removed. For full data, please refer to https://www.lissdata.nl/","storageIdentifier":"surf://store:17d689df06d-a7e661953f74","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"cdfcd8cf370834144604e8e114c45727af8eba43"},"tabularData":false,"creationDate":"2021-11-28","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"description":"The Python script used to code non-substantive responses and merge the results to dataset (L_Kinderwens_2021_nonres_Xiao_GS.csv)","label":"nonresponse.ipynb","restricted":false,"version":3,"datasetVersionId":3917,"dataFile":{"id":196737,"persistentId":"","filename":"nonresponse.ipynb","contentType":"application/x-ipynb+json","friendlyType":"Jupyter Notebook","filesize":42684,"description":"The Python script used to code non-substantive responses and merge the results to dataset (L_Kinderwens_2021_nonres_Xiao_GS.csv)","storageIdentifier":"surf://store:17cd343a0e5-520a9e8630f6","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"91096a10c5b1a847011889fcba2f2dfda9b21c24"},"tabularData":false,"creationDate":"2021-10-31","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"description":"Knitted version of paper1.Rmd","label":"paper1.html","restricted":false,"version":1,"datasetVersionId":3917,"dataFile":{"id":217615,"persistentId":"","filename":"paper1.html","contentType":"text/html","friendlyType":"HTML","filesize":2207202,"description":"Knitted version of paper1.Rmd","storageIdentifier":"surf://store:17de95c6cf5-91d5825b7fff","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"85e90efdd9e2e31b880361851d465c15a97658a7"},"tabularData":false,"creationDate":"2021-12-23","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"description":"Rmarkdown file for descriptive statistics, drawing graphs and regression analysis","label":"paper1.Rmd","restricted":false,"version":1,"datasetVersionId":3917,"dataFile":{"id":217616,"persistentId":"","filename":"paper1.Rmd","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":28458,"description":"Rmarkdown file for descriptive statistics, drawing graphs and regression analysis","storageIdentifier":"surf://store:17de95ccb37-9f65385495bd","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"886a7351cea005e95cfe4ce4ddddb54b54a970ad"},"tabularData":false,"creationDate":"2021-12-23","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"description":"The Python script used to extract response times and integrate to dataset (L_Kinderwens_2021_tscan_w_nonres_rt.csv)","label":"paradata.ipynb","restricted":false,"version":2,"datasetVersionId":3917,"dataFile":{"id":196735,"persistentId":"","filename":"paradata.ipynb","contentType":"application/x-ipynb+json","friendlyType":"Jupyter Notebook","filesize":50963,"description":"The Python script used to extract response times and integrate to dataset (L_Kinderwens_2021_tscan_w_nonres_rt.csv)","storageIdentifier":"surf://store:17cd343a15e-dc27fae80ec9","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"3bc080f93157370e9e055c7d495c0730644a3557"},"tabularData":false,"creationDate":"2021-10-31","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"description":"The Python script to extract open answers and turn them into individual .txt files, which were later processed by t-scan.","label":"preprocess_tscan.py","restricted":false,"version":2,"datasetVersionId":3917,"dataFile":{"id":216336,"persistentId":"","filename":"preprocess_tscan.py","contentType":"text/x-python","friendlyType":"Python Source Code","filesize":3314,"description":"The Python script to extract open answers and turn them into individual .txt files, which were later processed by t-scan.","storageIdentifier":"surf://store:17dda337e28-a55c91e92864","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"8670778b3622fea25cc7f1b8a6401f8718ae8245"},"tabularData":false,"creationDate":"2021-12-21","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}},{"label":"README.txt","restricted":false,"version":1,"datasetVersionId":3917,"dataFile":{"id":216338,"persistentId":"","filename":"README.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":1020,"storageIdentifier":"surf://store:17dda40d2fb-3ad2a6f5f5c4","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"719e6b1bc5ebe435ed972b4b1fd845145b7281e9"},"tabularData":false,"creationDate":"2021-12-21","publicationDate":"2026-03-10","lastUpdateTime":"2026-03-10T13:42:29Z","fileAccessRequest":false}}]}}}