Conference paper Open Access

Word Clustering for Historical Newspapers Analysis

Lidia Pivovarova; Jani Marjanen; Elaine Zosa


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3402940</identifier>
  <creators>
    <creator>
      <creatorName>Lidia Pivovarova</creatorName>
      <affiliation>University of Helsinki</affiliation>
    </creator>
    <creator>
      <creatorName>Jani Marjanen</creatorName>
      <affiliation>University of Helsinki</affiliation>
    </creator>
    <creator>
      <creatorName>Elaine Zosa</creatorName>
      <affiliation>University of Helsinki</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Word Clustering for Historical Newspapers Analysis</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-09-12</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3402940</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3402939</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/newseye</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This paper is a part of a collaboration between computer scientists and historians aimed at development of novel methods for historical newspapers analysis. We present a case study of ideological terms ending with -ism suffix in nineteenthcentury&lt;br&gt;
Finnish newspapers. We propose a two-step procedure to trace differences in word usages over time: training of diachronic embeddings on several time slices and when clustering embeddings of&amp;nbsp;selected words together with their neighbours&lt;br&gt;
to obtain historical context. The obtained&amp;nbsp;clusters turn out to be useful for historical studies. The paper also discusses&lt;br&gt;
specific difficulties related to development of historian-oriented tools.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/770299/">770299</awardNumber>
      <awardTitle>NewsEye: A Digital Investigator for Historical Newspapers</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
159
92
views
downloads
All versions This version
Views 159159
Downloads 9292
Data volume 83.6 MB83.6 MB
Unique views 150150
Unique downloads 8888

Share

Cite as