Extraction of places related to Flickr tags

Yukino Baba, Fuyuki Ishikawa, Shinichi Honiden

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

2 Citations (Scopus)

Abstract

Geographic information systems use databases to map keywords to places. These databases are currently most often created by using a top-down approach based on the geographic definitions. However, there is a problem with this approach in that these databases only contain location definitions such as addresses and place names, which does not allow for searches using keywords other than these words. Additionally, they do not give any information on the popularity, e.g., which is more popular among the places indexed by the same keyword. A bottom-up approach, based on the actual usage of words, can address these problems. We propose a method to aggregate tagging data and extract places related to a tag using the pair of a tag and a geo-tagged photo. We target the co-occurrence of a tag and the geolocation and represent the places related to a tag as a probability distribution over the longitudes and latitudes. We applied our method to data on the photo sharing service Flickr and experimentally confirmed that our method made it possible to highly-accurately extract places related to tags. Our direct bottom-up approach enables the extraction of place information that is not obtained by using traditional top-down approaches.

Original languageEnglish
Title of host publicationECAI 2010
PublisherIOS Press
Pages523-528
Number of pages6
ISBN (Print)9781607506058
DOIs
Publication statusPublished - 2010 Jan 1
Externally publishedYes

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume215
ISSN (Print)0922-6389

Fingerprint

Geographic information systems
Probability distributions

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Baba, Y., Ishikawa, F., & Honiden, S. (2010). Extraction of places related to Flickr tags. In ECAI 2010 (pp. 523-528). (Frontiers in Artificial Intelligence and Applications; Vol. 215). IOS Press. https://doi.org/10.3233/978-1-60750-606-5-523

Extraction of places related to Flickr tags. / Baba, Yukino; Ishikawa, Fuyuki; Honiden, Shinichi.

ECAI 2010. IOS Press, 2010. p. 523-528 (Frontiers in Artificial Intelligence and Applications; Vol. 215).

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

Baba, Y, Ishikawa, F & Honiden, S 2010, Extraction of places related to Flickr tags. in ECAI 2010. Frontiers in Artificial Intelligence and Applications, vol. 215, IOS Press, pp. 523-528. https://doi.org/10.3233/978-1-60750-606-5-523
Baba Y, Ishikawa F, Honiden S. Extraction of places related to Flickr tags. In ECAI 2010. IOS Press. 2010. p. 523-528. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-60750-606-5-523
Baba, Yukino ; Ishikawa, Fuyuki ; Honiden, Shinichi. / Extraction of places related to Flickr tags. ECAI 2010. IOS Press, 2010. pp. 523-528 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{260475813a9b441cb518d77d118a2e51,
title = "Extraction of places related to Flickr tags",
abstract = "Geographic information systems use databases to map keywords to places. These databases are currently most often created by using a top-down approach based on the geographic definitions. However, there is a problem with this approach in that these databases only contain location definitions such as addresses and place names, which does not allow for searches using keywords other than these words. Additionally, they do not give any information on the popularity, e.g., which is more popular among the places indexed by the same keyword. A bottom-up approach, based on the actual usage of words, can address these problems. We propose a method to aggregate tagging data and extract places related to a tag using the pair of a tag and a geo-tagged photo. We target the co-occurrence of a tag and the geolocation and represent the places related to a tag as a probability distribution over the longitudes and latitudes. We applied our method to data on the photo sharing service Flickr and experimentally confirmed that our method made it possible to highly-accurately extract places related to tags. Our direct bottom-up approach enables the extraction of place information that is not obtained by using traditional top-down approaches.",
author = "Yukino Baba and Fuyuki Ishikawa and Shinichi Honiden",
year = "2010",
month = "1",
day = "1",
doi = "10.3233/978-1-60750-606-5-523",
language = "English",
isbn = "9781607506058",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "523--528",
booktitle = "ECAI 2010",
address = "Netherlands",

}

TY - GEN

T1 - Extraction of places related to Flickr tags

AU - Baba, Yukino

AU - Ishikawa, Fuyuki

AU - Honiden, Shinichi

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Geographic information systems use databases to map keywords to places. These databases are currently most often created by using a top-down approach based on the geographic definitions. However, there is a problem with this approach in that these databases only contain location definitions such as addresses and place names, which does not allow for searches using keywords other than these words. Additionally, they do not give any information on the popularity, e.g., which is more popular among the places indexed by the same keyword. A bottom-up approach, based on the actual usage of words, can address these problems. We propose a method to aggregate tagging data and extract places related to a tag using the pair of a tag and a geo-tagged photo. We target the co-occurrence of a tag and the geolocation and represent the places related to a tag as a probability distribution over the longitudes and latitudes. We applied our method to data on the photo sharing service Flickr and experimentally confirmed that our method made it possible to highly-accurately extract places related to tags. Our direct bottom-up approach enables the extraction of place information that is not obtained by using traditional top-down approaches.

AB - Geographic information systems use databases to map keywords to places. These databases are currently most often created by using a top-down approach based on the geographic definitions. However, there is a problem with this approach in that these databases only contain location definitions such as addresses and place names, which does not allow for searches using keywords other than these words. Additionally, they do not give any information on the popularity, e.g., which is more popular among the places indexed by the same keyword. A bottom-up approach, based on the actual usage of words, can address these problems. We propose a method to aggregate tagging data and extract places related to a tag using the pair of a tag and a geo-tagged photo. We target the co-occurrence of a tag and the geolocation and represent the places related to a tag as a probability distribution over the longitudes and latitudes. We applied our method to data on the photo sharing service Flickr and experimentally confirmed that our method made it possible to highly-accurately extract places related to tags. Our direct bottom-up approach enables the extraction of place information that is not obtained by using traditional top-down approaches.

UR - http://www.scopus.com/inward/record.url?scp=77956036267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956036267&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-606-5-523

DO - 10.3233/978-1-60750-606-5-523

M3 - Conference contribution

AN - SCOPUS:77956036267

SN - 9781607506058

T3 - Frontiers in Artificial Intelligence and Applications

SP - 523

EP - 528

BT - ECAI 2010

PB - IOS Press

ER -