The work of the Web & Media group on the Semantic Culture Web has received world-wide attention and recognition. The MultimediaN E-Culture cultural search engine, developed in cooperation with UvA, CWI and a range of cultural-heritage institutions, won the Semantic Web Challenge 2006 in Athens (Georgia). This work now forms the heart of the research demonstrator for Europeana, the EU Culture portal launched in November 2008. The Web & Media group is a leading partner in the research projects for further development of Europeana, starting in 2009. The CHIP demonstrator (personalized museum tour, with Rijksmuseum Amsterdam) won the third prize at the 2007 Semantic Web Challenge. We are also involved in projects concerning annotation and access to TV archives (CHOICE, MuNCH, PrestoPRIME), personalized integration of TV and Web content (NoTube), historical events (Agora) and information integration for e-science (VL-e) and for maritine safety and security (Poseidon).


Public Screen (image Dropstuff/Ngage media
OBSERVE explores the use of a recommendation system for audiovisual content displayed in public spaces. Media companies are faced with the challenge of selecting content that is interesting and relevant to passers-by, yet re-usable to screen in different locations. Currently, audiovisual content is often pre-programmed in repetitive loops, ignoring the circumstances and the interests of the users. OBSERVE works on a new approach through 1) the use of high-quality interactive content, for which it aims to develop guidelines and best practices; and 2) the development of a context-sensitive content selection system. The role of the VU within OBSERVE will consist in the design of metadata models to describe context types, audiovisual content, and their relationship, and in assessing the potential of Linked Open Data to support the recommender and/or to enrich the audiovisual content.

Who: Astrid van Aggelen, Victor de Boer, Ronald Siebes.

Big Data Europe

The growing digitization and networking process within our society has a large influence on all aspects of everyday life. Large amounts of data are being produced permanently, and when they are analyzed and interlinked they have the potential to create new knowledge and intelligent solutions for both the economy and society as a whole. To facilitate the use of Big Data technologies, the European Union funds an interdisciplinary research and innovation project called “BigDataEurope”. A European consortium, is developing a platform that will simplify the creation and access to Big Data applications and their integration into existing workflows.

Who: Victor de Boer, Ronald Siebes, Paul Groth


In the digital cultural heritage project DIVE, we provide innovative access to heritage objects from heterogeneous online collections. We use historical events and event narratives as a context both for searching and browsing as well as for the presentation of individual and group of objects. Semantics from existing collection vocabularies and linked data vocabularies are used to link objects and the events, people, locations and concepts that are depicted or associated with those objects. An innovative interface allows for browsing this network of data in an intuitive fashion. The main focus in DIVE is to provide support to (1) digital humanities scholars and (2) general audience in their online explorations.

Who: Victor de Boer, Oana Inel, Lora Aroyo.

COMMIT Project: Data2Semantics

Data2Semantics aims to provide essential semantic infrastructure for bringing e-Science to the next level. A core task for scientific publishers is to speed up scientific progress by improving the availability of scientific knowledge. This holds both for dissemination of results through traditional publications, as well as through the publication of scientific data. The Data2Semantics project focuses on a key problem for data management in e-Science: How to share, publish, access, analyse, interpret and reuse data?

Who: Paul Groth, Michiel Hildebrand, Martine de Vos, Guus Schreiber, Jan Wielemaker

Talk of Europe

The Talk of Europe project (2014-2015) generates Linked Open Data from the plenary debates of the European Parliament. It covers the complete verbatim proceedings of the plenary sessions held between 1999 and 2014, in all available translations in 21 EU languages. This information is integrated with a database of political affiliations of the Members of Parliament and linked to other Linked Open Datasets, including dbPedia and Geonames. The resulting data of over 25 million triples are available through a user interface and a SPARQL endpoint. They enable queries about the monthly sessions, the agenda of the debates, the spoken words and their translations into other EU languages, integrated with extensive information about the speakers such as affiliations to countries, parties and committees. Talk of Europe is funded by CLARIN and NWO.

Who: Laura Hollink, Astrid van Aggelen, Ronald Siebes.


Development of solutions to enrich collections using Internet enabled reliable, scalable and cost effective collaborative content curation and to improve accessibility through advanced personalized content recommendation and search functionalities.

Who: Lora Aroyo, Chris Dijkshoorn, Jacco van Ossenbrugggen, Guus Schreiber


The CrowdTruth Framework implements an approach to machine-human computing for collecting annotation data on text, images and videos. The approach is focussed specifically on collecting gold standard data for training and evaluation of cognitive computing systems. The original framework was inspired by the IBM Watson project for providing improved (multi-perspective) gold standard (medical) text annotation data for the training and evaluation of various IBM Watson components, such as Medical Relation Extraction, Medical Factor Extraction and Question-Answer passage alignment.

Who: Lora Aroyo, Chris Welty, Oana Inel, Anca Dumitrache, Benjamin Timmermans


Amalgame builder from Michiel Hildebrand on Vimeo.

Amalgame is an interactive Alignment server under development at the VU University Amsterdam in the context of the PrestoPrime and EuropeanaConnect projects. Amalgame is built on top of the Cliopatria environment using SWI-Prolog. Amalgame is being further developed by Spinque under the name CultuurLink.

Who: Jacco van Ossenbrugggen, Michiel Hildebrand


ViSTA-TV is a European Union-funded research project with partners University of Zurich, Technical University Dortmund, Rapid-I GmbH, Zattoo Europa AG, Vrije Universiteit Amsterdam, and BBC. The partners TUDo, UZH, VUA, and the BBC investigate novel methods for giving recommendation to IPTV users on-the-fly. UZH and TUDo work on large-scale complex event processing on heterogeneous flows of data. VUA and the BBC perform research on enriching electronic program guide (EPG) data by Linked Data. TUDo is working on extracting features from the audio and video signals received by the IPTV providers.

WhoLora Aroyo, Valentina Maccatrozzo, Guus Schreiber

eScience project: BiographyNet

BiographyNet is a multidisciplinary project that combines expertise from history, computer science and computational linguistics. The project is a collaboration between the Netherlands eScience Center, Huygens ING and VU University Amsterdam. BiographyNet uses data from the Biography Portal of the Netherlands (BP), which contains approximately 125,000 biographies from a variety of Dutch biographical dictionaries. Through a combination of data enrichment, visualization and browsing techniques, BiographyNet wants to inspire historians to set up new research projects.

WhoAntske Fokkens, Serge ter Braake, Niels Ockeloen, Piek Vossen, Victor de Boer, Susan Legêne, Guus Schreiber

Dutch Ships and Sailors

Dutch Ships and Sailors is a project that aims to provide an infrastructure for maritime historical datasets, linking correlating data through semantic web technology. It brings together datasets related to recruitment and shipping in the East-India trade (mainly 18th century) and in the shipping of the northern provinces of the Netherlands (mainly 19thcentury).

Who: Victor de Boer

NWO CATCH Project: Agora

The Agora project is a collaboration between the History and Computer Science departments at the VU University Amsterdam, the Rijksmuseum Amsterdam and the Dutch national audiovisual archive Beeld en Geluid. The aim of Agora is to develop a social platform in which museum objects can be placed into an explicit (art)historic context. Through the (art)historic context, objects from highly diverse museum collections can be related, resulting in a more complete and illustrated description of historical events. End-users will also be allowed to create their own personal narratives which will lead to theoretical reflection on the meaning of digitally mediated public history in contemporary society. Check the Agora Demonstrators

Who: Lora Aroyo, Lourens van der Meij, Guus Schreiber, Chiel van Akker, Susan Legene

FP7 Project: VOICES

There is a widespread agreement that ICT services, especially mobile ones, have the potential to play a major role in furthering social and rural development in developing economies. The VOICES project is aimed at: (1) The leveraging of content that is locally relevant to actors and entrepreneurs who are of key importance to on-the-ground social and rural development. and (2) The removal of a range of access barriers (notably, limitations related to access channels, literacy, and languages) that currently hamper information/knowledge sharing and associated community building especially in rural areas. One 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.

Who: Victor de Boer, Chris van Aart, Nana Baah Gyan, Hans Akkermans

FP7 Project:  NewsReader

NewsReader processes news in 4 different languages when it comes in. It will extract what happened to whom, when and where, removing duplication, complementing information, registering inconsistencies and keeping track of the original sources. Any new information is integrated with the past, distinguishing the new from the old in an unfolding story line, similar to how people tend to remember the past and access knowledge and information. The difference here is that NewsReader can provide access to all original sources and will not forget any details (like a “History Recorder”). We will develop a decision-support tool that allows professional decision makers to explore these story lines using visual interfaces and interactions to exploit their explanatory power and their systematic structural implications. Likewise, NewsReader can make predictions from the past on future events or explain new events and developments through the past. NewsReader started in January 2013 and will run until January 2016.


This is a cross-disciplinary project which brings scholars from computer science and history together to complement each other in order to help build a novel semantic search approach for the Rijksmuseum Print Online Collection.

WhoLora Aroyo, Chris Dijkshoorn


Creating serendipity (i.e. “pleasant surprises for users”) is a primary goal of intelligent recommender systems. This project proposes an interdisciplinary approach to enhance the serendipity of TV recommendations that combines complementary knowledge from three disciplines – Computer Science, Language & Cognition and Communication Science. The project examines the “back-end” or algorithms behind serendipitous TV recommendations (Computer Science), the “front-end” or the actual display of these recommendations (Language & Cognition), and the “effect” on users’ perceptions and satisfaction (Communication Science).

Who: Lora Aroyo, Valentina Maccatrozzo, Esra Ateşçelik, Allison Eden, Paul Groth, Tilo Hartmann, Britt Hoeksema, Gerard Steen


Waisda? is a Web application to collect user-generated metadata for video clips. It follows the paradigm of games-with-a-purpose, where two or more users play against each other by entering tags that describe the content of the video. The goal of each player is to score points by entering the same tags as one of the other players. As a result each video that is played in the game is annotated with tags that are anchored to a time point in the video at which the tag was entered. Checkout the code of the opensource: Github

Waisda? Video tagging game demonstrator

BSIK Project: Poseidon

Information integration in maritine safety & security. Check out our demos: Poseidon demonstrators

Who: Willem van Hage, Veronique Malais, Guus Schreiber, Wan Fokkink


How do different media-outlets cover political news? The PoliMedia project aims to showcase the potential of cross-media analysis for research in the humanities, by curating automatically detected semantic links between data sets of different media types. PoliMedia is a collaboration between VU University Amsterdam, Erasmus University Amsterdam, Delft University of Technology and the Netherlands Institure for Sound and Vision.

Polimedia won the LinkedUp Veni Competition! Try our demo at or read our paper.

IPI/Furoba Blon

In the IPI Furoba Blon project, we build on VOICES technologies for a new use case: voice based citizen journalism in the Sahel region. 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.

Who: Victor de Boer, Chris van Aart, Nana Baah Gyan, Hans Akkermans


Personalized information prefestation for cultural heritage (at Rijksmuseum Amsterdam), Checkout the CHIP personalized museum tour demonstrator

WhoLora Aroyo, Yiwen Wang

FP7 IP Project: NoTube

Integrating TV and Web with semantics

Future TV is Now: Personalized & Social

Who: Lora Aroyo, Chris van Aart, Dan Brickley, Ronald Siebes, Guus Schreiber

FP7 IP Project: PrestoPRIME

User-generated metadata for TV archives

Who: Lora Aroyo, Riste Gligorov, Jacco van Ossenbrugggen, Guus Schreiber

FP7 e-ContentPlus Project: EuropeanaConnect

Methods and tools for semantic enrichment of collection metadata for the next version of Europeana cultural-heritage portal. Check out the Semantic Search Demonstrator.

Who: Antoine Isaac, Jacco van Ossenbrugggen, Guus Schreiber, Bob Wielinga, Jan Wielemaker, Victor de Boer

Verrijkt Koninkrijk

Providing improved access to Loe de Jong’s seminal work on Dutch history in WWII: in the demonstrator part of the project advanced tools and techniques are applied to gather data on De Jong’s perception of the much debated issue of pillarization (Dutch: ‘verzuiling’) and group identity. In the resource curation part of the project the corpus will be enriched and made available to the CLARIN-community for further research. provides Linked Data access to Loe de Jong’s work

Who: Victor de Boer


Ontology-based information disclosure in virtual e-schience lab

Who: Willem van Hage, Machiel Jansen, Guus Schreiber

MultimediaN E-Culture

Semantic annotation and search of virual heritage collections (BSIK, 2005-2009). Check out the MultimediaN E-Culture demonstrator

Who: Lora Aroyo, Borys Omelayenko, Jacco van Ossenbruggen, Guus Schreiber,  Ronald Siebes, Anna Tordai , Bob Wielinga, Jan Wielemaker


Semi-automatic semantic annotation of TV archives (at Sound & Vision)

Who: Veronique Malais&eacute, Luit Gazendam, Guus Schreiber


Knowledge enrichment by means of automated analyses of digital images and video (at Sound & Vision)

Who: Laura Hollink, Guus Schreiber

Knowledge Web

Baseline semantic-web technology (IST NoE, scientific coordinator, 2004-2007)

Who: Willem van Hage, Guus Schreiber


Interactive multiemdia for cultural heritage (NWO-TOKEN, 2003-2007)

Who: Mark van Assem, Guus Schreiber


Integrating knowledge analysis and video analysis

Who: Laura Hollink, Guus Schreiber, Bob Wielinga

Multimedia Information Analysis

Prelude project for MultimediaN E-Culture (ICES-KIS, 1998-2003)

Who: Guus Schreiber, Bob Wielinga, Jan Wielemaker


Range of Europeana projects in the nineties on methdology for knowledge engineering

Who: Guus Schreiber, Bob Wielinga, Jan Wielemaker


Semantic infrastrcuture for Dutch digital heritage (SenterNovem, 2009-2010)

Who: Lourens van der Meij, Jacco van Ossenbrugggen, Jan Wielemaker