I am an assistant professor (UD) at the Web & Media group at the Computer Science department of the Vrije Universiteit Amsterdam (VU). I am also a senior research fellow at Netherlands Institute for Sound and Vision. In my research, I combine (Semantic) Web technologies with Human-Computer Interaction, Knowledge Representation and Information Extraction to tackle research challenges in various domains. These include Cultural Heritage, Digital Humanities and ICT for Development (ICT4D). More information on these projects can be found on this site or through my CV .

Elevator Annotator: Local Crowdsourcing on Audio Annotation

[This post is based on Anggarda Prameswari’s Information Sciences MSc. Thesis]

For her M.Sc. Project, conducted at the Netherlands Institute for Sound and Vision (NISV), Information Sciences student Anggarda Prameswari (pictured right) investigated a local crowdsourcing application to allow NISV to gather crowd annotations for archival audio content. Crowdsourcing and other human computation techniques have proven their use for collecting large numbers of annotations, including in the domain of cultural heritage. Most of the time, crowdsourcing campaigns are done through online tools. Local crowdsourcing is a variant where annotation activities are based on specific locations related to the task.

The two variants of the Elevator Annotator box as deployed during the experiment.
The two variants of the Elevator Annotator box as deployed during the experiment.

Anggarda, in collaboration with NISV’s Themistoklis Karavellas, developed a platform called “Elevator Annotator”, to be used on-site. The platform is designed as a standalone Raspberry Pi-powered box which can be placed in an on-site elevator for example. It features a speech recognition software and a button-based UI to communicate with participants (see video below).

The effectiveness of the platform was evaluated in two different locations (at NISV and at Vrije Universiteit) and with two different modes of interaction (voice input and button-based input) through a local crowdsourcing experiment. In this experiments, elevator-travellers were asked to participate in an experiment. Agreeing participants were then played a short sound clip from the collection to be annotated and asked to identify a musical instrument.

The results show that this approach is able to achieve annotations with reasonable accuracy, with up to 4 annotations per hour. Given that these results were acquired from one elevator, this new form of crowdsourcing can be a promising method of eliciting annotations from on-site participants.

Furthermore, a significant difference was found between participants from the two locations. This indicates that indeed, it makes sense to think about localized versions of on-site crowdsourcing.

More information:

Share This:

Events panel at DHBenelux2017

At the Digital Humanities Benelux 2017 conference, the e-humanities Events working group organized a panel with the titel “A Pragmatic Approach to Understanding and Utilizing Events in Cultural Heritage”. In this panel, researchers from  Vrije Universiteit Amsterdam, CWI, NIOD, Huygens ING, and Nationaal Archief presented different views on Events as objects of study and Events as building blocks for historical narratives.

The session was packed and the introductory talks were followed by a lively discussion. From this discussion it became clear that consensus on the nature of Events or what typology of Events would be useful is not to be expected soon. At the same time, a simple and generic data model for representing Events allows for multiple viewpoints and levels of aggregations to be modeled. The combined slides of the panel can be found below. For those interested in more discussion about Events: A workshop at SEMANTICS2017 will also be organized and you can join!

Share This:

DIVE+ receives the Grand Prize at the LODLAM Summit in Venice

We are excited to announce that DIVE+ has been awarded the Grand Prize at the LODLAM Summit, held at the Fondazione Giorgio Cini this week. The summit brought together ~100 experts in the vibrant and global community of Linked Open Data in Libraries, Archives and Museums. It is organised bi-annually since 2011. Earlier editions were held in the US, Canada and Australia, making the 2017 edition the first in Europe.

The Grand Prize (USD$2,000) was awarded by the LODLAM community. It’s recognition of how DIVE+ demonstrates social, cultural and technical impact of linked data. The Open Data Prize (of USD$1,000) was awarded to WarSampo for its groundbreaking approach to publish open data

Fondazione Giorgio Cini. Image credit: Johan Oomen CC-BY

.Five finalists were invited to present their work, selected from a total of 21 submissions after an open call published earlier this year. Johan Oomen, head of research at the Netherlands Institute for Sound and Vision presented DIVE+ on day one of the summit. The slides of his pitch have been published, as well as the demo video that was submitted to the open call. Next to DIVE+ (Netherlands) and WarSampo (Finland) the finalists were Oslo public library (Norway), Fishing in the Data Ocean (Taiwan) and Genealogy Project (China). The diversity of the finalists is a clear indication that the use of linked data technology is gaining momentum. Throughout the summit, delegates have been capturing the outcomes of various breakout sessions. Please look at the overview of session notes and follow @lodlam on Twitter to keep track.

Pictured: Johan Oomen (@johanoomen) pitching DIVE+. Photo: Enno Meijers. 

DIVE+ is an event-centric linked data digital collection browser aimed to provide an integrated and interactive access to multimedia objects from various heterogeneous online collections. It enriches the structured metadata of online collections with linked open data vocabularies with focus on events, people, locations and concepts that are depicted or associated with particular collection objects. DIVE+ is the result of a true interdisciplinary collaboration between computer scientists, humanities scholars, cultural heritage professionals and interaction designers. DIVE+ is integrated in the national CLARIAH (Common Lab Research Infrastructure for the Arts and Humanities) research infrastructure.

Pictured: each day experts shape the agenda for that day, following the OpenSpace format. Image credit: Johan Oomen (cc-by)

DIVE+ is a collaborative effort of the VU University Amsterdam (Victor de Boer, Oana Inel, Lora Aroyo, Chiel van den Akker, Susane Legene), Netherlands Institute for Sound and Vision (Jaap Blom, Liliana Melgar, Johan Oomen), Frontwise (Werner Helmich), University of Groningen (Berber Hagendoorn, Sabrina Sauer) and the Netherlands eScience Centre (Carlos Martinez). It is supported by CLARIAH and NWO.

The LODLAM Challenge was generously sponsored by Synaptica. We would also like to thank the organisers, especially Valentine Charles and Antoine Isaac of Europeana and Ingrid Mason of Aarnet for all of their efforts. LODLAM 2017 has been a truly unforgettable experience for the DIVE+ team.

Share This:

Getting down with LOD tools at the 2nd CLARIAH Linked Data workshop

[cross-post from clariah.nl]

On Tuesday 13 June 2017, the second CLARIAH Linked Data workshop took place. After the first workshop in September which was very much an introduction to Linked Data to the CLARIAH community, we wanted to organise a more hands-on workshop where researchers, curators and developers could get their hands dirty.

The main goal of the workshop was to introduce relevant tools to novice as well as more advanced users. After a short plenary introduction, we therefore split up the group where for the novice users the focus was on tools that are accompanied by a graphical user interface, like OpenRefine and Gephi; whereas we demonstrated API-based tools to the advanced users, such as the CLARIAH-incubated COW, grlc, Cultuurlink and ANANSI. Our setup, namely to have the participants convert their own dataset to Linked Data and query and visualise, was somewhat ambitious as we had not taken into account all data formats or encodings. Overall, participants were able to get started with some data, and ask questions specific to their use cases.

It is impossible to fully clean and convert and analyse a dataset in a single day, so the CLARIAH team will keep investigating ways to support researchers with their Linked Data needs. For now, you can check out the CultuurLink slides and tutorial materials from the workshop and keep an eye out on this website for future CLARIAH LOD events.

Share This:

Kickoff meeting Mixed Methods in the Humanities projects

Last week, the Volkswagen Stiftung-funded “Mixed Methods’ in the Humanities?” programme had its kickoff meeting for all funded projects in in Hannover, Germany. Our ArchiMediaL project on enriching and linking historical architectural and urban image collections was one of the projects funded through this programme and even though our project will only start in September, we already presented our approach,  the challenges we will be facing and who will face them (our great team of post-docs Tino Mager, Seyran Khademi and Ronald Siebes). Group picture. Can you spot all the humanities and computer science people?Other interesting projects included analysing of multi-religious spaces on the Medieval World (“Dhimmis and Muslims”); the “From Bach to Beatles” project on representing music and schemata to support musicological scholarship as well as the nice Digital Plato project which uses NLP technologies to map paraphrasing of Plato in the ancient world. An overarching theme was a discussion on the role of digital / quantitative / distant reading methods in humanities research. The projects will run for three years so we have some time to say some sensible things about this in 2020.

 

 

Share This:

EVENTS2017 workshop at SEMANTiCS

An important role in the interpretation of cultural heritage collections is played by ‘historic events’. In the SEMANTiCS workshop Events2017: Understanding Events Semantics in Cultural Heritage, to be held on 11 Sept 2017, we will investigate and discuss challenges around identifying, representing, linking and reasoning about historical events. We invite full papers (8p) as well as short papers (4p) on this topic.

The call for papers is out now.  You have until July 10, 2017 to submite your contribution. Contributions can include original research papers, position papers, or papers describing tools, demonstrators or datasets. Accepted contributions will be published on the CEUR-WS website (or equivalent).

More information at https://events2017workshop.wordpress.com/

Share This:

ICT4D at Sustainability day

During the National Day for Sustainability (Nationale dag voor duurzaamheid in het hoger onderwijs 2017), the ICT4D team presented our current research and educational activities to the many participants of this event, hosted at VU. Anna Bon and myself presented our work on sustainable methodologies for ICT4D as well as current work on small and sustainable ICT platform (Kasadaka), see the slides below.

After this, the participants got a chance to meet our students and their very nice projects up close in an interactive demonstration session. Selected ICT4D students presented the voice-accessible services.

VD_201705236930

VD_201705236942_1

VD_201705236943

All photos by SURFSara, more pictures of the event can be found on Flickr.

Share This:

VU’s 4th ICT4D symposium: a look back

Yesterday, 18 May 2017, the 4th International ICT4D symposium was held at Vrije Universiteit Amsterdam.  The event was organized by the W4RA team and supported by VU Network Institute, the Netherlands Research School for Information and Knowledge Systems SIKS, VU Computer Science Department and VU International Office. Invited speakers from Ghana, France and the Netherlands highlighted this year’s theme was “Sustainability and ICT4D”.

Keynote speaker Gayo Diallo from Universite de Bordeaux discussed the possibilities of ICT for African Traditional Medicine (ATM). In his talk, he showed how semantic web technologies can play a role here to connect heterogeneous datasets for analytics and end-user services. Such services would need to be based on voice-interaction and localized technologies. His slides can be found here.

Chris van Aart from 2Coolmonkeys discussed a number of smartphone applications developed in the context of W4RA activities, including Mr. Jiri a tree-counting application. He proved there is a market for such applications in the African context (Slides).

After the break, Francis Dittoh from UDS Ghana discussed issues around sustainbility for a meteo application he is currently developing for Northern-Ghana (slides). Wendelien Tuijp from VU’s CIS then presented multiple perspectives on ICT4D (Slides). The symposium was closed by a video presentation from Aske Robenhagen, showcasing the ongoing work in Nepal around mapping knowledge networks and developing a smartphone application supporting information exchange for local accountability extension workers. More information on that project can be found at nepalnetworks.org/

The presentations of the day can be found through the links above. The entire symposium was live-streamed and you can watch it all on youtube or below.

Below is a lost of the approximate starting time of the various speakers in the video

  • 6m19 Dr. Gayo Diallo – Université de Bordeaux (FR): Towards a Digital African Traditional Healthcare using Semantic Web.
  • 56m28 Dr. Chris van Aart – 2CoolMonkeys BV (NL) : Developing Smartphone Apps for African farmers.
  • 1h30m00 break.
  • 1h52m00 Francis Dittoh – University for Development Studies (Ghana): ICT business development in rural Africa.
  • 2h23m00 Wendelien Tuyp – CIS-VU : Sustainable Community Initiatives and African Farmer Innovation.
  • 2h52m00 Aske Robenhagen Network Institute Academy Assistant VU – Building resilient applications for sustainable development. Better video of this can be found at https://www.youtube.com/watch?v=-hzRSo4TJtA

Share This:

Big Data Europe Platform paper at ICWE 2017

With the launch of the Big Data Europe platform behind us, we are telling the world about our nice platform and the many pilots in the societal challenge domains that we have executed and evaluated. We wrote everything down in one comprehensive paper which was accepted at the 7th international conference on Web Engineering (ICWE 2017) which is to be held in Rome next month.

High-level BDE architecture (copied from the paper Auer et al.)

The paper “The BigDataEurope Platform – Supporting the Variety Dimension of Big Data”  is co-written by a very large team (see below) and it presents the BDE platform — an easy-to-deploy, easy-to-use and adaptable (cluster-based and standalone) platform for the execution of big data components and tools like Hadoop, Spark, Flink, Flume and Cassandra.  To facilitate the processing of heterogeneous data, a particular innovation of the platform is the Semantic Layer, which allows to directly process RDF data and to map and transform arbitrary data into RDF. The platform is based upon requirements gathered from seven of the societal challenges put forward by the European Commission in the Horizon 2020 programme and targeted by the BigDataEurope pilots. It is validated through pilot applications in each of these seven domains. .A draft version of the paper can be found here.

 

The full reference is:

Sören Auer, Simon Scerri, Aad Versteden, Erika Pauwels, Angelos Charalambidis, Stasinos Konstantopoulos, Jens Lehmann, Hajira Jabeen, Ivan Ermilov, Gezim Sejdiu, Andreas Ikonomopoulos, Spyros Andronopoulos, Mandy Vlachogiannis, Charalambos Pappas, Athanasios Davettas, Iraklis A. Klampanos, Efstathios Grigoropoulos, Vangelis Karkaletsis, Victor de Boer, Ronald Siebes, Mohamed Nadjib Mami, Sergio Albani, Michele Lazzarini, Paulo Nunes, Emanuele Angiuli, Nikiforos Pittaras, George Giannakopoulos, Giorgos Argyriou, George Stamoulis, George Papadakis, Manolis Koubarakis, Pythagoras Karampiperis, Axel-Cyrille Ngonga Ngomo, Maria-Esther Vidal.   . Proceedings of The International Conference on Web Engineering (ICWE), ICWE2017, LNCS, Springer, 2017

 

Share This:

Dutch Ships and Sailors SPARQL handson exercises

I made some exercises a while ago but keep re-using them for SPARQL tutorials and hands on sessions. I now moved them to a new webpage. This page presents SPARQL queries in increasing complexity that one can copy-paste into the interactive query field of the Dutch Ships and Sailors live triple store.

Have fun with these Handson SPARQL excercises (updated May 2017)

Below you can also find the slides I used this tuesday for a workshop around Linked Data, Dutch Ships and Sailors and SPARQL, which form the introduction to the handson session.

Share This: