Geographic Context and Experience

The Geo Team in Barcelona does research on understanding a person's geographic context. We want to understand the way people name the places around them, how they use them, move through them, tag and talk about them.

 

What we do

The work of the group is divided into fundamental research which focuses on modeling human-centric geographies with social media. From this fundamental research, we have several applied projects in point of interest detection, geographic disambiguation, geographic scope and intent, and spatial indexing and caching. The applied research, in turn, serves as the foundation for a set of tools, APIs, and demos. We collaborate with universities, with scientists in Yahoo! Research and Yahoo! Labs, as well as the Geo-Technologies and Geo-Targeting product groups in Yahoo!.

People

  • The Team:
  • Vanessa Murdock, Research Scientist
  • Hugues Bouchard, Research Engineer
  • Diego Arechaga, Research Engineer
  • Adam Rae, Postdoctoral Researcher
  • Collaborators:
  • Y! Geo Technologies (Abbas Gassem, Product Manager)
  • Y! Geo Targeting (T. C. Cheng, Product Manager)
  • Marco Pennachiotti, Scientist, Y! Labs
  • Oren Kurland, Technion University
  • Marco Mamei, University of Modena
  • Neil O'Hare, Dublin City University
  • Adrian Popescu, CEA LIST
  • Interns:
  • Sam Huston, University of Massachusetts (2011)
  • Andrea Grechi, University of Trento (2010)
  • Sheila Kinsella, DERI National University of Ireland, Galway (2010)
  • Manos Papagelis, University of Toronto (2009)
  • Pavel Serdyukov, Twente University (2008)

GLOCAL

We are funded by the European Project GLOCAL. Glocal deals primarily with organizing information around events, and our research focuses on the geographic context of events, as well as ways to leverage user-generated content.

The GLOCAL Vision in a Nutshell

We describe the world using words. But words often call to mind different mental views of the world to different people, because of their differing personal experience and contexts. As a result, the semantic gap between our verbally expressed conceptualizations of the world and our actual experience of the world – which is most directly represented by media such as photos and videos – is far beyond the reach of current multimedia systems.

Hence we don’t yet have a universal way of contextualizing search, navigation and media management according to users’ needs and their operating environments.

A key idea underlying the Integrating Project GLOCAL is to use events as the primary means for organizing and indexing media. Events have a local and a global dimension. The local dimension involves the assignment of tags (conceptualizations) to media (personal experiences). The global dimension involves the sharing of general event structures and specific event descriptions, which enables social sharing and networking of events, tags and media.

Within networked communities, common (global) descriptions of the world can be built and continuously enriched by a continuous flow of individual (local) descriptions.

With two leading search companies and four content providers, the GLOCAL consortium will be able to realize and evaluate the GLOCAL approach in several application domains, which will involve professional and amateur users dealing with professional and generic contents.