<?xml version="1.0" encoding="UTF-8"?>
<resource xmlns="http://datacite.org/schema/kernel-4" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.5/metadata.xsd">
  <identifier identifierType="DOI">10.18710/VM2K4O</identifier>
  <creators>
    <creator>
      <creatorName nameType="Personal">Rettberg, Jill Walker</creatorName>
      <givenName>Jill Walker</givenName>
      <familyName>Rettberg</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org">https://orcid.org/0000-0003-2472-3812</nameIdentifier>
      <affiliation>University of Bergen</affiliation>
    </creator>
    <creator>
      <creatorName nameType="Personal">Wigers, Hermann</creatorName>
      <givenName>Hermann</givenName>
      <familyName>Wigers</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org">https://orcid.org/0009-0004-0676-7816</nameIdentifier>
      <affiliation>University of Bergen</affiliation>
    </creator>
  </creators>
  <titles>
    <title>A dataset of 1500-word stories generated by gpt-4o-mini for 236 nationalities</title>
  </titles>
  <publisher>DataverseNO</publisher>
  <publicationYear>2025</publicationYear>
  <subjects>
    <subject>Arts and Humanities</subject>
    <subject>Computer and Information Science</subject>
    <subject schemeURI="https://vocabularyserver.com/dhthesaurus/" subjectScheme="DH Thesaurus">digital humanities</subject>
    <subject schemeURI="https://www.wikidata.org/" subjectScheme="Wikidata">digital humanities</subject>
    <subject schemeURI="https://www.wikidata.org/" subjectScheme="Wikidata">generative AI</subject>
    <subject schemeURI="https://www.wikidata.org" subjectScheme="Wikidata">gpt-4o-mini</subject>
    <subject schemeURI="https://www.wikidata.org/" subjectScheme="Wikidata">narration</subject>
    <subject schemeURI="https://www.wikidata.org/" subjectScheme="Wikidata">generative artificial intelligence</subject>
    <subject schemeURI="https://www.wikidata.org" subjectScheme="Wikidata">large language model</subject>
    <subject schemeURI="https://www.wikidata.org/" subjectScheme="Wikidata">synthetic data</subject>
  </subjects>
  <contributors>
    <contributor contributorType="Producer">
      <contributorName nameType="Personal">AI STORIES</contributorName>
      <givenName>AI</givenName>
      <familyName>STORIES</familyName>
      <affiliation>Center for Digital Narrative, University of Bergen</affiliation>
    </contributor>
    <contributor contributorType="Distributor">
      <contributorName nameType="Organizational">University of Bergen</contributorName>
      <affiliation>Center for Digital Narrative</affiliation>
    </contributor>
    <contributor contributorType="ContactPerson">
      <contributorName nameType="Personal">Rettberg, Jill Walker</contributorName>
      <givenName>Jill Walker</givenName>
      <familyName>Rettberg</familyName>
      <affiliation>University of Bergen</affiliation>
    </contributor>
    <contributor contributorType="ProjectLeader">
      <contributorName nameType="Personal">Rettberg, Jill Walker</contributorName>
      <givenName>Jill Walker</givenName>
      <familyName>Rettberg</familyName>
    </contributor>
    <contributor contributorType="HostingInstitution">
      <contributorName nameType="Organizational">University of Bergen</contributorName>
    </contributor>
    <contributor contributorType="ResearchGroup">
      <contributorName nameType="Organizational">Center for Digital Culture</contributorName>
    </contributor>
    <contributor contributorType="Researcher">
      <contributorName nameType="Personal">Wigers, Hermann</contributorName>
      <givenName>Hermann</givenName>
      <familyName>Wigers</familyName>
    </contributor>
    <contributor contributorType="DataManager">
      <contributorName nameType="Personal">Wigers, Hermann</contributorName>
      <givenName>Hermann</givenName>
      <familyName>Wigers</familyName>
    </contributor>
    <contributor contributorType="ProjectMember">
      <contributorName nameType="Personal">Robinson, Colin</contributorName>
      <givenName>Colin</givenName>
      <familyName>Robinson</familyName>
    </contributor>
  </contributors>
  <dates>
    <date dateType="Submitted">2025-02-17</date>
    <date dateType="Available">2025-05-28</date>
    <date dateType="Collected">2025-01-13/2025-01-19</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset">AI-generated text</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType=":unav">10.5281/zenodo.14947238</alternateIdentifier>
    <alternateIdentifier alternateIdentifierType=":unav">https://github.com/AI-STORIES-ERC/GPT_stories</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="DOI">10.18710/VM2K4O/NALABP</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="DOI">10.18710/VM2K4O/GWEGQX</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="DOI">10.18710/VM2K4O/GEVNMF</relatedIdentifier>
  </relatedIdentifiers>
  <sizes>
    <size>18583</size>
    <size>42408986</size>
    <size>19740</size>
  </sizes>
  <formats>
    <format>text/comma-separated-values</format>
    <format>application/zip</format>
    <format>text/plain</format>
  </formats>
  <version>1.0</version>
  <rightsList>
    <rights rightsURI="info:eu-repo/semantics/openAccess"/>
    <rights rightsURI="http://creativecommons.org/publicdomain/zero/1.0" rightsIdentifier="CC0-1.0" rightsIdentifierScheme="SPDX" schemeURI="https://spdx.org/licenses/" xml:lang="en">Creative Commons CC0 1.0 Universal Public Domain Dedication.</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">We created a dataset of stories generated by OpenAI’s gpt-4o-miniby using a Python script to construct prompts that were sent to the OpenAI API. We used Statistics Norway’s list of 252 countries, added demonyms for each country, for example Norwegian for Norway, and removed countries without demonyms, leaving us with 236 countries. Our base prompt was  “Write a 1500 word potential {demonym} story”, and we generated 50 stories for each country.

The scripts used to generate the data, and additional scripts for analysis are available at the GitHub repository https://github.com/MachineVisionUiB/GPT_stories</description>
    <description descriptionType="TechnicalInfo">Python, 3.11</description>
    <description descriptionType="TechnicalInfo">OpenAI API, gpt-4o-mini</description>
    <description descriptionType="TechnicalInfo">distilbert-base-uncased-emotion, not specified</description>
    <description descriptionType="TechnicalInfo">TextBlob, 0.19.0</description>
  </descriptions>
  <geoLocations>
    <geoLocation>
      <geoLocationPlace>Bergen, Norway</geoLocationPlace>
    </geoLocation>
  </geoLocations>
  <fundingReferences>
    <fundingReference>
      <funderName>European Research Council</funderName>
      <awardNumber>101142306</awardNumber>
    </fundingReference>
    <fundingReference>
      <funderName>Research Council of Norway</funderName>
      <awardNumber>332643</awardNumber>
    </fundingReference>
  </fundingReferences>
</resource>
