23-27 March 2015, Amsterdam. At the Meertens Institute
The Talk of Europe – Travelling CLARIN Campus project aims to facilitate and stimulate pan-European collaboration in the Humanities, Social Sciences and Computer Science, based on the proceedings of the European Parliament (EP) by organising three international creative camps in 2014 and 2015. These proceedings are a rich source for humanities and social sciences researchers that focus on areas such as European History, integration and politics. Given their multilinguality they are also a rich source for linguists. The Talk of Europe (TOE) project team has made these proceeding available as Linked Data for reuse and research purposes. They contain the debates in the EP from July 1999 onwards, including all available translations in 22 languages. The creative camp intends to stimulate and explore this rich source by bringing together academics from the humanities, social sciences, computer science and related disciplines.
For our second creative camp we invite teams to submit proposals that are driven by Humanities a/o Social Science research questions and that can 1) be addressed by the EP proceedings, exploiting web and natural language processing techniques and 2) can possibly add new knowledge and functionality to the dataset. The goal is to develop proof-of-concept tools and/or datasets that can be applied in scholarly research in the social sciences and humanities, or that provide insights into the EP to European citizens. Researchers who have an idea for a proposal but no contact with developers or vice versa, can contact the organisers who will try to match participants where possible.
We will select proposals that aim to use and/or enrich the proceedings of the European Parliament to address a research question. Underlying example questions are clarified by a possible technique or enrichment. Relevant topics and techniques include but are not limited to:
– What kind of topics are discussed in the European Parliament?
The only topic information given for a debate is the title. It would be interesting to annotate debates with theme keywords, deploying automated topic detection, or classify the debates in an existing taxonomy.
– How do Members of the European Parliament vote?
Enriching the proceedings with data on the voting behaviour of individual members of the EP. This information might need to be extracted from the EU website.
– To what extent do Members of the European Parliament use and refer to official reports during the debates?
– Enriching the dataset with the official reports, which are available on the EU website (in HTML) and/or detecting references to reports in debate texts and titles and creating links.
– To what extent do members of the European Parliament deliberate on topics that are being discussed in their party programs?
Establishing links from debates to party programs of the parties that participate in the European Parliament
– How are debates covered in the media?
Discovering links between debates and media coverage (newspaper, radio, magazine or television) of the topics discussed in parliament
– How are debates discussed on social media?
Discovering links to social media in which the topics under debate are being addressed
– Is there a relation between debates in national parliaments and the European Parliament?
Creating links to proceedings of National Parliaments.
European Parliament Dataset
The proceedings of the European Parliament have been converted to RDF, which is a widely used standard for representing and interchanging structured data, and linking to other data sources. Moreover, the data are enriched with biographical and political information on the speakers. Furthermore, the dataset lends itself to be linked with resources in other European countries, such as parliamentary records, social media or news reports. The EP proceedings in RDF format, a SPARQL endpoint and a description of the data are available on the Talk of Europe data portal. It supports querying in free text and in the semantic web query language SPARQL (version 1.1). For the latter, a URL (endpoint) is available to send requests to, and the portal collects several interfaces.
The event will comprise five consecutive days in which participants will mainly work on their project but the week will also include 1) presentations by humanities scholars and political scientists on how they use political datasets, 2) presentations by computer scientists showing best practices from other projects and 3) practical sessions for tool development.
Bursaries covering travel to and from the venue and accommodation in the period 23-27 March will be available for participants working in EU or associated countries.
Submission of proposals
In order to participate, the TOE organisers welcome your proposal. Submissions should be no longer than 1 A4 page and should describe the following:
- The topic and research question to be addressed
- The technique that will be deployed
- The dataset(s), tool(s), or method(s) that you plan to use.
- The intended outcome of your participation including a description of how the result will be made available after the creative camp.
- Contact info and keywords describing research interests for all participants who would like to attend and a confirmation the participants can attend the full week.
Criteria for acceptance
- Proposals will be assessed based on clarity, feasibility and expected impact.
- In order to be eligible for the bursary, participants must work in an EU or Associated Country.
- If possible, resulting datasets should be made openly available in standard formats (e.g. CLARIN standards)
- Datasets to be linked with the EP data may be from any type or source.
- Researchers, Master or PhD students, academics further in their career and non-academic developers are all welcome.
- Proposals that include cross-border collaboration will be prioritized.
- Proposals will be ranked on the basis of individual quality, the research question, and on global criteria such as thematic, geographical and linguistic distribution.
- Submissions due: 30 January 2015
- Acceptance notification: 6 February 2015
- Camp: 23-27 March 2015 (5 days)
The creative camp will be held 23-27 March at the Meertens Institute, Amsterdam, the Netherlands
About the project
The Talk of Europe project is conducted within the framework of CLARIN (Common Language Resources and Technology Infrastructure), which aims to equip scholars in the humanities and social sciences with easy and sustainable access to digital language data through advanced tools.
Talk of Europe – Travelling CLARIN Campus is a collaboration of:
- Erasmus University Rotterdam & Erasmus Studio
o Jill Briggeman, MA
o Dr. Martijn Kleppe
o Prof. dr. Henri Beunders
- VU University Amsterdam
o Astrid van Aggelen, MSc
o Dr. Laura Hollink
o Marnix van Berchum MA
- Netherlands Institute for Sound and Vision
o Jaap Blom
o Johan Oomen, MA
- CLARIN-NL & CLARIN ERIC (initiators)
o Steven Krauwer
o Prof. dr. Jan Odijk
Made possible by support of NWO and the Dutch ministry of OCW.
For further information and questions, please contact Jill Briggeman (email@example.com).