Conference paper Open Access

Word Clustering for Historical Newspapers Analysis

Lidia Pivovarova; Jani Marjanen; Elaine Zosa


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/6fd970a1-09f8-422d-9ce7-422a7a2a689a/Word_Clustering_for_Historical_Newspapers_Analysis.pdf"
      }, 
      "checksum": "md5:f5a5f2d37c946511e2ba35e9966adaad", 
      "bucket": "6fd970a1-09f8-422d-9ce7-422a7a2a689a", 
      "key": "Word_Clustering_for_Historical_Newspapers_Analysis.pdf", 
      "type": "pdf", 
      "size": 908235
    }
  ], 
  "owners": [
    58661
  ], 
  "doi": "10.5281/zenodo.3402940", 
  "stats": {
    "version_unique_downloads": 88.0, 
    "unique_views": 150.0, 
    "views": 159.0, 
    "version_views": 159.0, 
    "unique_downloads": 88.0, 
    "version_unique_views": 150.0, 
    "volume": 83557620.0, 
    "version_downloads": 92.0, 
    "downloads": 92.0, 
    "version_volume": 83557620.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3402940", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3402939", 
    "bucket": "https://zenodo.org/api/files/6fd970a1-09f8-422d-9ce7-422a7a2a689a", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3402939.svg", 
    "html": "https://zenodo.org/record/3402940", 
    "latest_html": "https://zenodo.org/record/3402940", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3402940.svg", 
    "latest": "https://zenodo.org/api/records/3402940"
  }, 
  "conceptdoi": "10.5281/zenodo.3402939", 
  "created": "2019-09-09T15:18:29.174147+00:00", 
  "updated": "2020-01-20T17:11:30.390678+00:00", 
  "conceptrecid": "3402939", 
  "revision": 5, 
  "id": 3402940, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3402940", 
    "description": "<p>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<br>\nFinnish 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&nbsp;selected words together with their neighbours<br>\nto obtain historical context. The obtained&nbsp;clusters turn out to be useful for historical studies. The paper also discusses<br>\nspecific difficulties related to development of historian-oriented tools.</p>", 
    "language": "eng", 
    "title": "Word Clustering for Historical Newspapers Analysis", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3402939"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3402940"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "770299", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::770299"
        }, 
        "title": "NewsEye: A Digital Investigator for Historical Newspapers", 
        "acronym": "NewsEye", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "communities": [
      {
        "id": "newseye"
      }
    ], 
    "publication_date": "2019-09-12", 
    "creators": [
      {
        "affiliation": "University of Helsinki", 
        "name": "Lidia Pivovarova"
      }, 
      {
        "affiliation": "University of Helsinki", 
        "name": "Jani Marjanen"
      }, 
      {
        "affiliation": "University of Helsinki", 
        "name": "Elaine Zosa"
      }
    ], 
    "meeting": {
      "acronym": "LT-DHA 2019", 
      "url": "https://www.inf.uni-hamburg.de/inst/dmp/hercore/publications/ltdha.html", 
      "dates": "5th September 2019", 
      "place": "Varna Bulgaria", 
      "title": "Language Technology for Digital Historical Archives (Workshop collocated with RANLP 2019)"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3402939", 
        "relation": "isVersionOf"
      }
    ]
  }
}
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