{"dcterms:modified":"2026-05-10","dcterms:creator":"Harvard Dataverse","@type":"ore:ResourceMap","schema:additionalType":"Dataverse OREMap Format v1.0.2","dvcore:generatedBy":{"@type":"schema:SoftwareApplication","schema:name":"Dataverse","schema:version":"6.10.1 build iqss-3","schema:url":"https://github.com/iqss/dataverse"},"@id":"https://dataverse.harvard.edu/api/datasets/export?exporter=OAI_ORE&persistentId=https://doi.org/10.7910/DVN/N67BDI","ore:describes":{"author":{"citation:authorName":"Bernhard-Harrer, Jana","citation:authorAffiliation":"Universität Wien","authorIdentifierScheme":"ORCID","authorIdentifier":"https://orcid.org/0000-0002-7632-2802"},"citation:producer":{"citation:producerName":"Enter your name here: LastName, FirstName"},"citation:dsDescription":{"citation:dsDescriptionValue":"copy directly from abstract in PSRM publicationAs the use of computational text analysis in the social sciences has increased, topic modeling has emerged as a popular method for identifying latent themes in textual data. Nevertheless, concerns have been raised regarding the validity of the results produced by this method, given that it is largely automated and inductive in nature, and the lack of clear guidelines for validating topic models has been identified by scholars as an area of concern. In response, we conducted a comprehensive systematic review of 789 studies that employ topic modeling. Our goal is to investigate whether the field is moving towards a common framework for validating these models. The findings of our review indicate a notable absence of standardized validation practices and a lack of convergence towards specific methods of validation. This gap may be attributed to the inherent incompatibility between the inductive, qualitative approach of topic modeling and the deductive, quantitative tradition that favors standardized validation. To address this, we advocate for incorporating qualitative validation approaches, emphasizing transparency and detailed reporting to improve the credibility of findings in computational social science research, when using topic modeling.","citation:dsDescriptionDate":"2025-04-24"},"citation:datasetContact":{"citation:datasetContactName":"Bernhard-Harrer, Jana","citation:datasetContactAffiliation":"Universität Wien","citation:datasetContactEmail":"jana.bernhard@univie.ac.at"},"title":"Replication Data for: Beyond Standardization: A Comprehensive Review of Topic Modeling Validation Methods for Computational Social Science Research","subject":"Social Sciences","dateOfDeposit":"2025-04-24","citation:depositor":"Bernhard-Harrer, Jana","@id":"https://doi.org/10.7910/DVN/N67BDI","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"2.0","schema:name":"Replication Data for: Beyond Standardization: A Comprehensive Review of Topic Modeling Validation Methods for Computational Social Science Research","schema:dateModified":"Mon Apr 28 14:12:33 EDT 2025","schema:datePublished":"2025-04-25","schema:creativeWorkStatus":"RELEASED","schema:license":"http://creativecommons.org/publicdomain/zero/1.0","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":false},"schema:includedInDataCatalog":"Harvard Dataverse","schema:isPartOf":{"schema:name":"Political Science Research and Methods (PSRM) Dataverse","@id":"https://dataverse.harvard.edu/dataverse/PSRM","schema:description":"<b><a href=\"http://journals.cambridge.org/ram\">Political Science Research and Methods (PSRM)</a></b> is the official journal of the European Political Science Association. It publishes original scholarly work of the highest quality from all subfields of political science with particular focus on research applying rigorous methods to empirical and theoretical problems.\n<br><br>\nPSRM is a signatory of the <a href=\"http://www.dartstatement.org/\">Data Access and Research Transparency (DA-RT) statement</a>, promoting data sharing and research transparency in political science. PSRM requires that authors make materials available to enable others to replicate the results of research. This Dataverse is dedicated to that material.\n<br><br>\nFor more information about contributing to the journal, see the <a href=\"http://assets.cambridge.org/RAM/RAM_ifc.pdf\">instructions for contributors</a>. Authors uploading datasets should see the <a href=\"http://journals.cambridge.org/images/fileUpload/documents/RAM_Dataverse_Guidelines.pdf\">guide to using PSRM Dataverse</a>.\n","schema:isPartOf":{"schema:name":"Harvard Dataverse","@id":"https://dataverse.harvard.edu/dataverse/harvard","schema:description":"<span><span><span><h3>Share, archive, and get credit for your data. Find and cite data across all research fields.</h3></span></span></span>"}},"ore:aggregates":[{"schema:name":"ReplicationDataset.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":443008,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=11115379","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/11115379","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":148676,"dvcore:storageIdentifier":"s3://dvn-cloud:19669c1a434-230dab2d56fb","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"http://www.w3.org/2001/04/xmldsig-more#md5","@value":"46e1ebf09df0772a085144293d9607b3"}},{"schema:name":"ReplicationNotebook.ipynb","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":443008,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=11116681","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/11116681","@type":"ore:AggregatedResource","schema:fileFormat":"application/x-ipynb+json","dvcore:filesize":1215548,"dvcore:storageIdentifier":"s3://dvn-cloud:19671089928-3f123c73f6bf","dvcore:rootDataFileId":11115380,"dvcore:previousDataFileId":11115380,"dvcore:checksum":{"@type":"http://www.w3.org/2001/04/xmldsig-more#md5","@value":"7b26419812dd9f012ba04613a537d3da"}},{"schema:name":"ReplicationNotebook_Log.pdf","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":443008,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=11115381","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/11115381","@type":"ore:AggregatedResource","schema:fileFormat":"application/pdf","dvcore:filesize":1977433,"dvcore:storageIdentifier":"s3://dvn-cloud:19669c1d3c3-546dd02d6859","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"http://www.w3.org/2001/04/xmldsig-more#md5","@value":"30b69a6bbb6383e39f35be9ecaccad65"}}],"schema:hasPart":["https://dataverse.harvard.edu/file.xhtml?fileId=11115379","https://dataverse.harvard.edu/file.xhtml?fileId=11116681","https://dataverse.harvard.edu/file.xhtml?fileId=11115381"]},"@context":{"author":"http://purl.org/dc/terms/creator","authorIdentifier":"http://purl.org/spar/datacite/AgentIdentifier","authorIdentifierScheme":"http://purl.org/spar/datacite/AgentIdentifierScheme","citation":"https://dataverse.org/schema/citation/","content":"@value","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","lang":"@language","ore":"http://www.openarchives.org/ore/terms/","personName":"https://schema.org/name","schema":"http://schema.org/","scheme":"http://www.w3.org/2004/02/skos/core#inScheme","subject":"http://purl.org/dc/terms/subject","termName":"https://schema.org/name","title":"http://purl.org/dc/terms/title"}}