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.

Talk of Europe – Linking European Parliament Proceedings

2,068 views

Published on

Talk held in DHBenelux 2014 by Astrid van Aggelen. Presents the project Talk of Europe, which makes available the plenary debates in the European Parliament, including all translations, as linked open data. Focus of the talk is on the data sources used and how this information is modelled, as well as the possibilities of the resulting RDF dataset in humanities research.

Published in: Data & Analytics, Technology
  • Be the first to comment

Talk of Europe – Linking European Parliament Proceedings

  1. 1. Talk of Europe Linking European Parliament Proceedings Astrid van Aggelen - VU University Amsterdam Max Kemman (@MaxJ_K) - Erasmus University Rotterdam
  2. 2. About the project ● Astrid van Aggelen ● Laura Hollink ● Max Kemman ● Martijn Kleppe ● Henri Beunders ● Marnix van Berchum ● Johan Oomen ● Jaap Blom ● Steven Krauwer ● Jan Odijk ● 2014-2015 ● Funded by CLARIN-NL & CLARIN ERIC
  3. 3. Primary goals plenary sessions 1996 - (present) ● Represent in Resource Description Framework
  4. 4. Primary goals plenary sessions 1996 - (present) ● Publish as linked open data
  5. 5. Primary goals plenary sessions 1996 - (present) ● Promote applications
  6. 6. The European Parliament session sessionDay agendaItem speech
  7. 7. The European Parliament Plenary sessions are NOT ● strictly role-based ● mirror of law-making ● interactive
  8. 8. Datasets 1. Europarl debate registry date, debates, speakers, speeches who said what in which debate on which day?
  9. 9. Data model
  10. 10. Data model
  11. 11. Enriching the data (1) ? What is a member’s political background?
  12. 12. Datasets ● Europarl debate registry debates, speakers, speeches ● Europarl MEP database parties, committee, country, delegation
  13. 13. Data model
  14. 14. Data model
  15. 15. Data model
  16. 16. Enriching the data (2) How to categorise debates? ?
  17. 17. Enriching the data (2) ● Foreign Affairs ● Human Rights ● Security and Defence ● Development ● International Trade ● Budgets ● Budgetary Control ● Economic and Monetary Affairs ● Employment and Social Affairs ● Environment, Public Health and Food Safety ● Industry, Research and Energy ● Internal Market and Consumer Protection ● Transport and Tourism ● Regional Development ● Agriculture and Rural Development ● Fisheries ● Culture and Education ● Legal Affairs ● Civil Liberties, Justice and Home Affairs ● Constitutional Affairs ● Women's Rights and Gender Equality ● Petitions
  18. 18. Datasets ● Europarl debate registry debates, speakers, speeches, texts* ● Europarl MEP database party, committee, country, delegation ● Europarl report registry committee / theme
  19. 19. Data model
  20. 20. Data model
  21. 21. Enriching the data (3) In which role is this person speaking?
  22. 22. Enriching the data (3) Heuristic processing!
  23. 23. Ideas for applications ● data enrichment: geographical dataset, encyclopedia, voting info (Eur-Lex) ● applications: topic preference of speakers by country / geography / party cross-lingual language use sentiment analysis
  24. 24. Creative camp ● Bring together developers and academic researchers from across Europe ● Promoting inventive use of the EP dataset, exploiting web and natural language processing techniques to add new knowledge and functionality to the dataset ● 6-10 October 2014 at NISV (Hilversum, The Netherlands) ● Submissions due: Friday 20 June www.talkofeurope.eu/cfp
  25. 25. More info General info: www.talkofeurope.eu Creative camp: www.talkofeurope.eu/cfp/ Astrid a.e.van.aggelen@vu.nl Max kemman@eshcc.eur.nl / @MaxJ_K

×