header

Georeferencing Flickr Photos Using Language Models at Different Levels of Granularity: An Evidence Based Approach

21 Pages Posted: 3 Jul 2018 Publication Status: Accepted

See all articles by Olivier Van Laere

Olivier Van Laere

Ghent University - Department of Information Technology

Steven Schockaert

Cardiff University - School of Computer Science & Informatics

Barth Dhoedt

Ghent University - Department of Information Technology

Abstract

The topic of automatically assigning geographic coordinates to Web 2.0 resources based on their tags has recently gained considerable attention. However, the coordinates that are produced by automated techniques are necessarily variable, since not all resources are described by tags that are  sufficiently descriptive. Thus there is a need for adaptive  techniques that assign locations to photos at the right level of granularity, or, in some cases, even refrain from making any  estimations regarding location at all. To this end, we consider  the idea of training language models at different levels of  granularity, and combining the evidence provided by these  language models using Dempster and Shafer’s theory of  evidence. We provide experimental results which clearly confirm  that the increased spatial awareness that is thus  gained allows us to make better informed decisions, and moreover increases the overall accuracy of the individual  language models.

Keywords: Dempster-Shafer evidence theory, Language models, Georeferencing, Web 2.0, Geographic information retrieval

Suggested Citation

Van Laere, Olivier and Schockaert, Steven and Dhoedt, Barth, Georeferencing Flickr Photos Using Language Models at Different Levels of Granularity: An Evidence Based Approach (2012). Journal of Web Semantics First Look, Available at SSRN: https://ssrn.com/abstract=3198976 or http://dx.doi.org/10.2139/ssrn.3198976

Olivier Van Laere (Contact Author)

Ghent University - Department of Information Technology ( email )

Jozef Plateaustraat 22
Ghent
Belgium

Steven Schockaert

Cardiff University - School of Computer Science & Informatics ( email )

Queens Building, 5 The Parade
Cardiff
United Kingdom

Barth Dhoedt

Ghent University - Department of Information Technology ( email )

Jozef Plateaustraat 22
Ghent
Belgium

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
219
Downloads
3
PlumX Metrics