Automatic discovery of global and local equivalence relationships in labeled geo-spatial data

Bart Thomee, Gianmarco Morales

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We propose a novel algorithmic framework to automatically detect which labels refer to the same concept in labeled spatial data. People often use different words and synonyms when referring to the same concept or location. Furthermore these words and their usage vary across culture, language, and place. Our method analyzes the patterns in the spatial distribution of labels to discover equivalence relationships. We evaluate our proposed technique on a large collection of geo-referenced Flickr photos using a semi-automatically constructed ground truth from an existing ontology. Our approach is able to classify equivalent tags with a high accuracy (AUC of 0.85), as well as providing the geographic extent where the relationship holds.

Original languageEnglish
Title of host publicationHT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery
Pages158-168
Number of pages11
ISBN (Print)9781450329545
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event25th ACM Conference on Hypertext and Social Media, HT 2014 - Santiago, Chile
Duration: 1 Sep 20144 Sep 2014

Other

Other25th ACM Conference on Hypertext and Social Media, HT 2014
CountryChile
CitySantiago
Period1/9/144/9/14

    Fingerprint

Keywords

  • flickr
  • folksonomy
  • geo-spatial analysis
  • geotagged data
  • relationship discovery

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Thomee, B., & Morales, G. (2014). Automatic discovery of global and local equivalence relationships in labeled geo-spatial data. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media (pp. 158-168). Association for Computing Machinery. https://doi.org/10.1145/2631775.2631794