{"dcterms:modified":"2026-06-24","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-4","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/7C6FNO","ore:describes":{"author":[{"citation:authorName":"Samuel, Jim","authorIdentifierScheme":"ORCID","authorIdentifier":{"personName":"Samuel, Jim","@id":"https://orcid.org/0000-0002-7599-3209","scheme":"ORCID","@type":"https://schema.org/Person"}},{"citation:authorName":"Siritha Chidipothu","authorIdentifierScheme":"ORCID","authorIdentifier":{"@id":"https://orcid.org/0009-0004-1482-1165","scheme":"ORCID","@type":"https://schema.org/Person"}},{"citation:authorName":"Khanna, Tanya","authorIdentifierScheme":"ORCID","authorIdentifier":{"personName":"Khanna, Tanya","@id":"https://orcid.org/0009-0009-0107-4160","scheme":"ORCID","@type":"https://schema.org/Person"}},{"citation:authorName":"Lakra, Ashish","authorIdentifierScheme":"ORCID","authorIdentifier":{"personName":"Lakra, Ashish","@id":"https://orcid.org/0009-0006-7581-2240","scheme":"ORCID","@type":"https://schema.org/Person"}},{"citation:authorName":"Vidhi Gala"}],"contributor":[{"citation:contributorName":"Jim Samuel"},{"citation:contributorName":"Tanya Khanna"},{"citation:contributorName":"Ashish Lakra"},{"citation:contributorName":"Vidhi Gala"}],"citation:dsDescription":{"citation:dsDescriptionValue":"The Global Artificial Intelligence News Headlines (GAIN-H) is an open-access public informatics collection of three complementary datasets containing over 2.5 million artificial intelligence-related news headlines gathered from global news sources across multiple languages, countries, and time periods. The repository was created to support interdisciplinary research on how artificial intelligence is represented, framed, and discussed within the public sphere.\n\nThe collection includes: (1) a metadata-rich corpus with temporal, linguistic, and URL-structural features; (2) a large-scale longitudinal corpus optimized for temporal analysis; and (3) an extended multilingual corpus containing search-term metadata that enables keyword-stratified analysis of AI discourse. Together, these datasets span more than two decades of AI-related news coverage and provide researchers with resources for studying media framing, sentiment, public discourse, AI governance, communication, computational social science, and natural language processing.\n\nThe repository is intended for researchers, policymakers, educators, journalists, practitioners seeking to examine trends in AI-related media coverage across time, geography, language, and thematic domains. The datasets are released to promote transparency, reproducibility, and evidence-based research on the societal implications of artificial intelligence.\n\nThe datasets were developed as part of the RAISE (Rethinking AI for Shared Empowerment) initiative at the MPI Program, Bloustein School, Rutgers University, and AIXosphere AI behavioral trends research."},"citation:datasetContact":{"citation:datasetContactEmail":"sc2855@scarletmail.rutgers.edu"},"title":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus","subject":["Computer and Information Science","Social Sciences"],"dateOfDeposit":"2026-06-03","@id":"https://doi.org/10.7910/DVN/7C6FNO","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.1","schema:name":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus","schema:dateModified":"Tue Jun 09 15:21:12 EDT 2026","schema:datePublished":"2026-06-05","schema:creativeWorkStatus":"RELEASED","schema:license":"http://creativecommons.org/publicdomain/zero/1.0","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":true},"schema:includedInDataCatalog":"Harvard Dataverse","schema:isPartOf":{"schema:name":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus","@id":"https://dataverse.harvard.edu/dataverse/global_artificial_intelligence_news_headlines_corpus","schema:description":"The Global Artificial Intelligence News Headlines (GAIN-H) is an open-access public informatics collection of three complementary datasets containing over 2.5 million artificial intelligence-related news headlines gathered from global news sources across multiple languages, countries, and time periods. The repository was created to support interdisciplinary research on how artificial intelligence is represented, framed, and discussed within the public sphere. The collection includes: (1) a metadata-rich corpus with temporal, linguistic, and URL-structural features; (2) a large-scale longitudinal corpus optimized for temporal analysis; and (3) an extended multilingual corpus containing search-term metadata that enables keyword-stratified analysis of AI discourse. Together, these datasets span more than two decades of AI-related news coverage and provide researchers with resources for studying media framing, sentiment, public discourse, AI governance, communication, computational social science, and natural language processing. The repository is intended for researchers, policymakers, educators, journalists, practitioners seeking to examine trends in AI-related media coverage across time, geography, language, and thematic domains. The datasets are released to promote transparency, reproducibility, and evidence-based research on the societal implications of artificial intelligence. The datasets were developed as part of the RAISE (Rethinking AI for Shared Empowerment) initiative at the MPI Program, Bloustein School, Rutgers University, and AIXosphere AI behavioral trends research.\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":"Global Artificial Intelligence News (GAIN) Corpus Dataset 1.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":735461,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=13987192","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/13987192?format=original","@type":"ore:AggregatedResource","schema:fileFormat":"text/comma-separated-values","dvcore:filesize":35471851,"dvcore:storageIdentifier":"s3://dvn-cloud-iqss:19e8e8aa2ff-87f4195a131b","dvcore:currentIngestedName":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus Dataset 1.tab","dvcore:UNF":"UNF:6:QQyeZ85+ugQm8lFmZK+2kg==","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"http://www.w3.org/2001/04/xmldsig-more#md5","@value":"c6f3da52f28f417e235a16f87931d8cc"}},{"schema:name":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus Dataset 2.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":735461,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=13989194","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/13989194?format=original","@type":"ore:AggregatedResource","schema:fileFormat":"text/comma-separated-values","dvcore:filesize":36684225,"dvcore:storageIdentifier":"s3://dvn-cloud-iqss:19e93ddf008-9e91b83ff39f","dvcore:currentIngestedName":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus Dataset 2.tab","dvcore:UNF":"UNF:6:XXazCN8Yef4e/4Y+gOXORw==","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"http://www.w3.org/2001/04/xmldsig-more#md5","@value":"83eb9df202cdb4eb4dcd0532c54c5415"}},{"schema:name":"Global Artificial Intelligence News Headlines (GAIN-H) Corpus Dataset 3.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":735461,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=13987190","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/13987190","@type":"ore:AggregatedResource","schema:fileFormat":"text/comma-separated-values","dvcore:filesize":1047600713,"dvcore:storageIdentifier":"s3://dvn-cloud-iqss:19e8e90c125-e4a16324601c","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"http://www.w3.org/2001/04/xmldsig-more#md5","@value":"7d56464ee82a7f2b7f4bbc1a5ea5a70a"}}],"schema:hasPart":["https://dataverse.harvard.edu/file.xhtml?fileId=13987192","https://dataverse.harvard.edu/file.xhtml?fileId=13989194","https://dataverse.harvard.edu/file.xhtml?fileId=13987190"]},"@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/","contributor":"http://purl.org/dc/terms/contributor","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","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","title":"http://purl.org/dc/terms/title"}}