Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

05. de boer dutchships

605 views

Published on

KB symposium historische kranten als big data,
Den Haag, 24 maart 2015

Published in: Government & Nonprofit
  • Be the first to comment

  • Be the first to like this

05. de boer dutchships

  1. 1. Dutch Ships and Sailors Victor de Boer - v.de.boer@vu.nl Digitale historische kranten als big data 24-3-2015 DIVE
  2. 2. Dutch Ships and Sailors Victor de Boer, Matthias van Rossum, Jur Leinenga, Rik Hoekstra With input from Andrea Bravo Balado and Robin Ponstein Netherlands Institute for Sound and Vision / VU University Amsterdam v.de.boer@vu.nl
  3. 3. The Problem: ((Maritime) historical) data is not integrated 25+ Maritime datasets; Heterogeneous
  4. 4. The solution Well, Linked Data obviously!
  5. 5. KB Delpher Dutch-Asiatic Shipping (DAS) – Voyages (Huygens ING) “VOC Opvarenden” Mustering and payroll information (DANS Easy) Dutch Ships and Sailors Jur Leinenga (Huygens ING) Monsterrollen Noordelijke provincies Matthias van Rossum (VU-hist) Generale Zeemonsterrollen VOC
  6. 6. DAS GZMVOC MDB VOCOPV Begunstig den VOCOPV Soldijboek en PROV AAT VOCOPV Opvaren den foaf owl:sameAs dss:hasKBLink rdfs:subClassOf, rdfs:subPropertyOf dss:DAS link skos :exactMatch
  7. 7. Links to original scans
  8. 8. Linking to Historical newspapers • Use ML to detect links between ships and historical newspaper articles (delpher.nl) – Features: ship name, time intervals, captain’s names, ship type, named entities, keywords, background knowledge • 179,120 links - Andrea Bravo Balado
  9. 9. Example [HARLINGEN, 24 October.] . «et gestrande Zweedsche schip , waarvan wij ons vorig no. melding maakten , is door de 'eepboot van hier afgebragt en hier binnengede u BiJ die gelegenheid werd ons medegeeeid, dat nog vier vaartuigen op Terschelling aren gestrand. Tevens is het berigt ontvan°e > dat het hier behoorende schoonerschip Transit, kapitein Schaap, in de Noordzee is gezonken, nadat het achterschip was weggeslagen ; een ligtmatroos verloor daarbij het leven. Mede zijn hier drie vreemde schepen met meer en minder zware averij binnengeloopen. Spoiler alert! It sank in the North Sea.
  10. 10. Data analysis and visualisation
  11. 11. Results • 30 Million RDF triples of integrated maritime historical data – 180.000 links to KB newspapers (Background information on arrivals, departures, cargo, other events ) – New visualisations and query options – Conversion process documented to allow for additional datasets (current work) – Online RDF triple store at Huygens ING • Linked Data principles are a great fit to digital history requirements – Heterogeneous models/datasets, light-weight reusable integration – Multiple levels of normalisation, through separate named graphs (including links to newspapers) – SW Provenance matches Historical Provenance • Watch out when you sail your Schooner into the North Sea
  12. 12. DIVE INTO THE EVENT-BASED BROWSING OF LINKED HISTORICALMEDIA VICTORDEBOER,JOHANOOMEN,OANAINEL,LORAAROYO, ELCO VANSTAVEREN,WERNERHELMICHANDDENNISDEBEURS
  13. 13. DIGITAL HUMANITIES RESEARCHERS MediaresearcherLarsArveRøsslandoftheUniversityofBergen.(Photo:AndreasR.Graven) https://www.flickr.com/photos/drainrat/14779928998/ EXPLORATIVE SEARCH Erp, M. van; Oomen, J.; Segers, R.; Akker, C. van de; Aroyo, L.; Jacobs, G.; Legêne, S; Meij, L. van der; Ossenbruggen, J.R. van; Schreiber, G. Automatic Heritage Metadata Enrichment with Historic Events Museums and the Web 2011 http://www.museumsandtheweb.com/mw2011/papers/automatic_heritage_metadata_enrichment_with_hi
  14. 14. DATA: OPENIMAGES.EU Open videos Netherlands Institute for Sound and Vision 3000, mostly news broadcasts
  15. 15. DATA: DELPHER.NL Scans of Radio bulletins (hand annotated) • 1937 – 1984 • 1.5 Million OCR’ed and NErred
  16. 16. ENTITY EXTRACTION CROWDTRUTH.ORG ENTITY EXTRACTION EVENTS CROWDSOURCING AND LINKING TO CONCEPTS THROUGH CROWDTRUTH.ORG SEGMENTATION & KEYFRAMES LINKING EVENTS AND CONCEPTS TO KEYFRAMES
  17. 17. MEDIA OBJECTS LINKED THROUGH EXTRACTED ENTITIES DIVE:MEDIA OBJECT SEM:EVENT SEM:PLACE SEM:TIME SEM:ACTOR SKOS:CONCEPT OA:ANNOTATION LINKS TO EUROPEANA LINKS TO DBPEDIA SIMPLE EVENT MODEL (SEM), OPENANNOTATION (OA) AND SKOS
  18. 18. INFINITY OF EXPLORATION https://www.flickr.com/photos/mibuchat/2774251415https://www.flickr.com/photos/benjcarson/245171885 DIGITAL SUBMARINE UI
  19. 19. DEMO DIVE.BEELDENGELUID.NL
  20. 20. THANK YOU https://www.flickr.com/photos/robysaltori/ DUTCHSHIPSANDSAILORS.NL DIVE.BEELDENGELUID.NL v.de.boer@vu.nl
  21. 21. http://semanticweb.cs.vu.nl/dss/user/query # Give me all records that have both a link to an original scan and one to a KB news article, that have an associated ship whose shiptype is a subtype of "kustvaarders". prefix dss: <http://purl.org/collections/nl/dss/> prefix mdb: <http://purl.org/collections/nl/dss/mdb/> SELECT * WHERE { ?record dss:hasOriginalScan ?scan. ?record dss:has_kb_link ?kblink. ?record mdb:schip ?schip. ?schip dss:has_shiptype ?shiptype. ?shiptype skos:exactMatch ?em. ?em skos:broader ?b. } LIMIT 50

×