Biography


Since November 2014, I work as a Data Scientist at Blueshift Labs, a San Francisco based startup in customer segmentation. We receive millions of daily user events on our clients' properties (mobile apps or desktop), which we store and organise in our data warehouses. The data science team them digs into this pile of data to compute scores for individual users, make recommendations and divide the user base into different segments that can be used by our clients. Our work directly impacts marketing campaings and revenues.

Before moving to the Bay Area, I worked at Yahoo! Labs in Barcelona, Spain, between September 2013 and November 2014 as a Research Engineer in the Web Mining group. There, I was doing data mining on huge (web-scale!) amounts of data from the Web. Next to internal Yahoo projects, I worked on the EU FP7 Limosine project. I was also doing research on geo-related Flickr data, related to the topic of my PhD thesis.

I obtained my PhD degree in Computer Science from Ghent University in 2013 on the topic of "Georeferencing Text Using Social Media". Over the past few years, I've been working on mining geographical information from large datasets of social media content (up to 100 million training items), which were obtained by web crawling.

Before my PhD, I obtained a Master of Science degree in Computer Science (Ghent University, 2004, licentiaat), studied at the Universidad Politecnica de Valencia (UPV), Spain, as a foreign exchange student (Erasmus 2004-2005), and received the Engineering degree of Master of Science in Computer Science (Ghent University, 2007, burgerlijk ingenieur ICT).

As of Oct 1st 2006, I have been a researcher at the Internet Based Communication Networks and Services (IBCN) research group of Ghent University. Next to the research for my PhD, I have been teaching various lab courses over the years to more than 2200 bachelor students in engineering and computer science such as: Programming in Java (6 semesters, 2006-2012), Software Engineering I and II (5 semesters, 2006-2011) and engineering projects about Google PageRank (1 semester, 2008) and the famous Lego NXT Robots (2 semesters, 2009-2010).

Expertise
Scalable machine learning on hadoop (pig + python, mapreduce, hive, AWS), (web scale) data mining, (geographic) information retrieval , natural language processing, personalisation and recommendation, drupal, context awareness, peer-to-peer

Resume

You can find a copy of my resume here.

Contact

PhD Dissertation

Georeferencing Text Using Social Media. March 18th, 2013, Ghent University, Belgium.[PDF]

Publications

  1. Driving Curiosity in Search with Large-scale Entity Networks
    Ilaria Bordino, Mounia Lalmas, Yelena Mejova, Olivier Van Laere
    Submitted for the ACM Sigweb Autumn newsletter, August 2014.

  2. DEESSE: entity-Driven Exploratory and sErendipitous Search SystEm
    Olivier Van Laere, Ilaria Bordino, Yelena Mejova, Mounia Lalmas
    To appear in proceedings of CIKM'2014, Shangai, China, November 2014.

  3. The Benchmark as a Research Catalyst: Charting the Progress of Geo-prediction for Social Multimedia
    Martha Larson, Pascal Kelm, Adam Rae, Claudia Hauff, Bart Thomee, Michele Trevisiol, Jaeyoung Choi, Olivier Van Laere, Steven Schockaert, Gareth J.F. Jones, Pavel Serdyukov, Vanessa Murdock, Gerald Friedland
    Submitted and under review as a book chapter for the book "Multimodal Location Estimation of Videos and Images", published by Springer, June 2014.

  4. Georeferencing Flickr Resources Based on Multimodal Features
    Pascal Kelm, Sebastian Schmiedeke, Steven Schockaert, Thomas Sikora, Michele Trevisiol, Olivier Van Laere
    Submitted and under review as a book chapter for the book "Multimodal Location Estimation of Videos and Images", published by Springer, June 2014.

  5. Georeferencing Wikipedia documents using data from social media sources
    Olivier Van Laere, Steven Schockaert, Vlad Tanasescu, Chris Jones, Bart Dhoedt
    ACM Transactions on Information Systems 32(3):12, January 2014

  6. Spatially-aware term selection for Flickr photo geotagging
    Olivier Van Laere, Jonathan Quinn, Steven Schockaert, Bart Dhoedt
    IEEE Transactions on Knowledge and Data Engineering 26(1):221-234, January 2014.

  7. Georeferencing Flickr resources based on textual meta-data
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Information Sciences 238(1):5274, July 2013.

  8. Detecting Places Of Interest using Social Media
    Steven Van Canneyt, Steven Schockaert, Olivier Van Laere, Bart Dhoedt
    Accepted for the 2012 IEEE/WIC/ACM International Conference on Web Intelligence, December 2012

  9. Georeferencing Flickr photos using language models at different levels of granularity: an evidence based approach [PDF]
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Journal of Web Semantics 16(1):17- 31, November 2012.

  10. Using Social Media to Find Places of Interest: A Case Study in London (best paper award)
    Steven Van Canneyt, Steven Schockaert, Olivier Van Laere, Bart Dhoedt
    Proceedings of the First ACM SIGSPATIAL International Workshop on Crowdsourced and Volunteered Geographic Information, November 2012

  11. Ghent and Cardiff University at the 2012 Placing Task[PDF]
    Olivier Van Laere, Steven Schockaert, Jonathan A. Quinn, Frank C. Langbein, Bart Dhoedt
    Working Notes of the 2012 MediaEval Workshop, October 2012

  12. Hybrid reasoning technique for improving context-aware applications [PDF]
    Matthias Strobbe, Olivier Van Laere, Bart Dhoedt, Filip De Turck and Piet Demeester
    Knowledge and Information Systems 31(3):581- 616, June 2012.

  13. Integrating location and context information for novel personalised applications
    Matthias Strobbe, Olivier Van Laere, Femke Ongenae, Samuel Dauwe, Bart Dhoedt, Filip De Turck and Piet Demeester
    IEEE Pervasive Computing 11(2):64-73, April-June 2012.

  14. Georeferencing in Social Networks
    Pascal Kelm, Vanessa Murdock, Sebastian Schmiedeke, Steven Schockaert, Pavel Serdyukov, Olivier Van Laere
    Book Chapter in Social Media Retrieval, Springer, 2012. ISBN 978-1-4471-4554-7

  15. Ghent University at the 2011 Placing Task (distinctive mention) [PDF]
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Working Notes of the 2011 MediaEval Workshop, 2011

  16. Georeferencing Wikipedia pages using language models from Flickr [PDF]
    Chris De Rouck, Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Proceedings of the Terra Cognita 11 Workshop, 2011

  17. Time-dependent recommendation of tourist attractions using Flickr[PDF]
    Steven Van Canneyt, Steven Schockaert, Olivier Van Laere, Bart Dhoedt
    Proceedings of the 23rd Benelux Conference on Artificial Intelligence (BNAIC), 2011

  18. Finding locations of Flickr resources using language models and similarity search [PDF]
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Proceedings of the First ACM International Conference on Multimedia Retrieval (ICMR), 2011

  19. Enriching auto-visual chat with conversation-based image retrieval and display
    Jeroen Vanattenhoven, Christof Van Nimwegen, Matthias Strobbe, Olivier Van Laere et al.
    Proceedings of the ACM Multimedia 2010 international conference, 2010

  20. Ghent University at the 2010 Placing Task (quantum leap award) [PDF]
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Working Notes of the 2010 MediaEval Workshop, 2010

  21. Interest based selection of user generated content for rich communication services
    Matthias Strobbe, Olivier Van Laere, Samuel Dauwe, Bart Dhoedt et al.
    Journal of Network and Computer Applications (JNCA), 2010.

  22. Combining Multi-Resolution Evidence for Georeferencing Flickr Images [PDF]
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Proceedings of the Fourth International Conference on Scalable Uncertainty Management (SUM), p. 347-360, 2010

  23. Towards Automated Georeferencing of Flickr Photos [PDF]
    Olivier Van Laere, Steven Schockaert, Bart Dhoedt
    Proceedings of the 6th Workshop on Geographic Information Retrieval, 7 pages, 2010

  24. Location-based service enabling platform for cultural heritage environments
    Samuel Dauwe, Matthias Strobbe, Olivier Van Laere, Filip De Turck et al.
    Proceedings of the International Conference on Wireless Networks (ICWN), 2009

  25. Tag based generation of user profiles
    Matthias Strobbe, Olivier Van Laere, Bart Bogaerts, Samuel Dauwe et al.
    Proceedings of the International Conference on Internet Computing (ICOMP), 2009

  26. Enriching Networked Applications and Services through User-Generated Content [PDF]
    Olivier Van Laere, Matthias Strobbe, Koen Michiels, Steven Schockaert, Samuel Dauwe, Jeroen Vanattenhoven, Christof van Nimwegen, Pieter Dhondt, Tim Verbelen, Bart Dhoedt, Filip De Turck, Piet Demeester
    Proceedings of the 48th FITCE Congress, p. 14-18, 2009

  27. Managing and using context aware information [PDF]
    Olivier Van Laere, Matthias Strobbe
    Proceedings of the 10th UGent-FirW Doctoraatssymposium, 2009

  28. Automatic learning of user interests for personalized communication services
    Matthias Strobbe, Olivier Van Laere
    Proceedings of the 9th UGent-FirW Doctoraatssymposium, 2008

  29. Efficient management of user interests for personalized communication services
    Matthias Strobbe, Olivier Van Laere, Samuel Dauwe, Filip De Turck et al.
    Proceedings of the 5th International IEEE Workshop on Management of Ubiquitous Communications and Services (MUCS), 2008

  30. Context based selection of user generated content
    Matthias Strobbe, Olivier Van Laere, Bruno Volckaert, Filip De Turck et al.
    Proceedings of the International Conference on Semantic Web & Web Services (SWWS), 2008

  31. Enabling platform for mobile content generation based on 2D barcodes [PDF]
    Olivier Van Laere, Matthias Strobbe, Philip Leroux, Bart Dhoedt et al.
    Proceedings of the International Conference on Internet Computing (ICOMP), 2008

  32. Interest based selection of user generated content for rich multimedia services [PDF]
    Olivier Van Laere, Matthias Strobbe, Samuel Dauwe, Bart Dhoedt et al.
    Proceedings of the 9th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), 2008

  33. Design of CASP: an open enabling platform for context aware office and city services
    Matthias Strobbe, Jan Hollez, Gregory De Jans, Olivier Van Laere et al.
    Proceedings of the 4th International Workshop on Managing Ubiquitous Communications and Services (MUCS), 2007

Technical Program Committee

  1. DIR 2012, 12th Dutch-Belgian Information Retrieval Workshop, Ghent, 23-24 February 2012
  2. Geotagging and its applications in Multimedia, Nara, Japan, 2 November 2012
  3. Geotagging and its applications in Multimedia, November 3-7, 2014, Orlando, Florida, USA
  4. CIKM 2014, November 3-7, 2014, Shangai, China