As a researcher, I have been working with great pleasure on Computer Science research challenges in the field of Cultural Heritage, Digital Humanities and ICT for Development. My main contributions are in the field of (Semantic) Web science while attempting to embed my research in a social context. My research interests include understanding and innovating the interaction between low-level digital technologies and high-level social processes. Below you find a number of current and past projects that form the context of my research, click on the title to view posts related to the project.
- Big Data Europe The Horizon2020 Big Data Europe project will undertake the foundational work for enabling European companies to build innovative multilingual products and services based on semantically interoperable, large-scale, multi-lingual data assets and knowledge, available under a variety of licenses and business models.
- Observe (2014-…) In the OBSERVE project, we look at how interactive content for public screens can be modelled. These content and context models could be used for automated content selection or recommendation.
- DIVE and DIVEplus (jul 2014-…) In the DIVE project, we will be looking at providing event-based browsing of (audiovisual and other) cultural heritage content. This content is extracted using automated methods and crowdsourcing. Check out our live demonstrator atdive.frontwise.com.
- Dutch Ships and Sailors (mar 2013-apr 2014)As a sea-faring nation, a large portion of Dutch history is found on the water. However, much of the digitized historical source material is still scattered across many databases and archives. This curation and demonstrator project aims to bring together the rich maritime historical data preserved in the many different databases. We propose a (semantic) web-based infrastructure that will house various maritime-historical datasets. We will provide a tool chain and methodology for converting legacy datasets. The infrastructure includes common vocabularies to normalize and enrich existing data. Links are established between the datasets and to other relevant datasets on the Web. Although the infrastructure will be set up to facilitate 25+ identified datasets, we initially populate the infrastructure with four selected datasets. These will allow us to investigate two case studies in order to answer the historical research question “To what extent did patterns of shipping and recruitment in the Dutch maritime sector change over the course of the 18th and 19th centuries?”
- Verrijkt Koninkrijk (feb 2012-mar 2013) Dr Loe de Jong’s Het Koninkrijk der Nederlanden in de Tweede Wereldoorlog remains the most appealing history of German occupied Dutch society (1940-1945). Published between 1969 and 1991, the 30 volumes still combine the qualities of an authoritative work for a general audience, and an inevitable point of reference for scholars. Ths project partners are NIOD Institute for War, Holocaust and Genocide Studies (NIOD), University of Amsterdam (UvA), Vrije Universiteit Amsterdam (VUA), Meertens Institute and Data Archiving and Networked Services (DANS-KNAW). The VUA part consists of constructing vocabularies out of OCR’ed indices and Named Entity Recognition results. These will be mapped to in-house thesauri as well as external Linked Data sources.
- EuropeanaConnect (2010-feb 2012) Previously I worked on the EuropeanaConnect project, where we try to convert and align existing data and metadata sources for European cultural heritage institutions to semantic structures. EuropeanaConnect is a technology provider for the Europeana project. Within this project, I worked on the conversion of data to the Europeana Data Model (EDM), examples include the data from the Amsterdam Museum, which is now available as Linked Open Data. I am also involved in the development of an interactive and transparant tool for vocabulary alignment, Amalgame (Amsterdam Alignment Metatool).
- VOICES (2011-20 14) Since June 2011 I am also involved in the VOICES project, headed at the VUA by Hans Akkermans, in this project we are building voice-based mobile web services for rural Africa. A related project is Web for Regreening in Africa (W4RA). Our first use case uses voice-based services to support local farmers. This leads to the so-called RadioMarché service, which is a local market information system that integrates GSM, ICT and Radio technologies.
- Furoba Blon (jan 2012-dec 2012) The Voices/W4RA team received additional funding by winning the IPI news contest. This will allow us to use much of the same techniques in a new use case: voice based citizen journalism in the Sahel region. The project has been named Foroba Blo, Furoba literally means “big field” or “collective field” but the signification is “for everyone” Blon = the vestibule where the chief holds his audience. Together they signify the large room or space where everyone has the right to speak in front of the chief; the truth can be told; but only if you do it respectfully, without insulting anyone.
- MultimediaN E-culture From 2003-2008 I was a Ph.D. student at the UvA under supervision of Bob Wielinga and Maarten van Someren at the Human-Computer Studies Lab of the University of Amsterdam (UvA). During that period I contributed to the MultimediaN E-culture project. I received my Ph.D. in september 2010. The title of my Ph.D thesis is “Ontology Enrichment from Heterogeneous Sources on the Web”.
- Siteguide (2008-2010) From 2008-2010 I worked as a postdoctoral researcher on the SiteGuide project where I developed methods and tools for automatic assesment and recommendation for web site authoring and design.