Extracting locations related to tags on folksonomy

Yukino Baba, Fuyuki Ishikawa, Shinichi Honiden

Research output: Contribution to journalArticle

Abstract

Geographic information systems use databases to map keywords to locations. Currently, these databases are mostly created by a top-down approach based on geographic definitions. Problems are that (1) these databases only have information about addresses, location names, landmarks, and stores, and (2) if there are multiple candidate locations for a keyword, these databases do not have the information about which location is popular. A bottom-up approach which targets actual usage of keywords can address these problems. We propose a method to aggregate tagging data and extract locations related to a tag by using pairs of a tag and a geotagged resource. We use cooccurrence of a tag and a location and represent the locations related to a tag as a probability distribution over longitudes and latitudes. We apply our method to data on the photo sharing service Flickr. We experimentally confirm that our method can extract locations related to tags with high accuracy. Our bottom-up approach enables the extraction of location information that is unavailable using traditional top-down approaches.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume27
Issue number1
DOIs
Publication statusPublished - 2012 Jan 1
Externally publishedYes

Fingerprint

Geographic information systems
Probability distributions

Keywords

  • Folksonomy
  • Geographic information
  • Tag semantics

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Extracting locations related to tags on folksonomy. / Baba, Yukino; Ishikawa, Fuyuki; Honiden, Shinichi.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 27, No. 1, 01.01.2012, p. 1-9.

Research output: Contribution to journalArticle

@article{cd1ddb4a6dd54ae2bcd9db6d803fbf47,
title = "Extracting locations related to tags on folksonomy",
abstract = "Geographic information systems use databases to map keywords to locations. Currently, these databases are mostly created by a top-down approach based on geographic definitions. Problems are that (1) these databases only have information about addresses, location names, landmarks, and stores, and (2) if there are multiple candidate locations for a keyword, these databases do not have the information about which location is popular. A bottom-up approach which targets actual usage of keywords can address these problems. We propose a method to aggregate tagging data and extract locations related to a tag by using pairs of a tag and a geotagged resource. We use cooccurrence of a tag and a location and represent the locations related to a tag as a probability distribution over longitudes and latitudes. We apply our method to data on the photo sharing service Flickr. We experimentally confirm that our method can extract locations related to tags with high accuracy. Our bottom-up approach enables the extraction of location information that is unavailable using traditional top-down approaches.",
keywords = "Folksonomy, Geographic information, Tag semantics",
author = "Yukino Baba and Fuyuki Ishikawa and Shinichi Honiden",
year = "2012",
month = "1",
day = "1",
doi = "10.1527/tjsai.27.1",
language = "English",
volume = "27",
pages = "1--9",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "1",

}

TY - JOUR

T1 - Extracting locations related to tags on folksonomy

AU - Baba, Yukino

AU - Ishikawa, Fuyuki

AU - Honiden, Shinichi

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Geographic information systems use databases to map keywords to locations. Currently, these databases are mostly created by a top-down approach based on geographic definitions. Problems are that (1) these databases only have information about addresses, location names, landmarks, and stores, and (2) if there are multiple candidate locations for a keyword, these databases do not have the information about which location is popular. A bottom-up approach which targets actual usage of keywords can address these problems. We propose a method to aggregate tagging data and extract locations related to a tag by using pairs of a tag and a geotagged resource. We use cooccurrence of a tag and a location and represent the locations related to a tag as a probability distribution over longitudes and latitudes. We apply our method to data on the photo sharing service Flickr. We experimentally confirm that our method can extract locations related to tags with high accuracy. Our bottom-up approach enables the extraction of location information that is unavailable using traditional top-down approaches.

AB - Geographic information systems use databases to map keywords to locations. Currently, these databases are mostly created by a top-down approach based on geographic definitions. Problems are that (1) these databases only have information about addresses, location names, landmarks, and stores, and (2) if there are multiple candidate locations for a keyword, these databases do not have the information about which location is popular. A bottom-up approach which targets actual usage of keywords can address these problems. We propose a method to aggregate tagging data and extract locations related to a tag by using pairs of a tag and a geotagged resource. We use cooccurrence of a tag and a location and represent the locations related to a tag as a probability distribution over longitudes and latitudes. We apply our method to data on the photo sharing service Flickr. We experimentally confirm that our method can extract locations related to tags with high accuracy. Our bottom-up approach enables the extraction of location information that is unavailable using traditional top-down approaches.

KW - Folksonomy

KW - Geographic information

KW - Tag semantics

UR - http://www.scopus.com/inward/record.url?scp=84856990015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856990015&partnerID=8YFLogxK

U2 - 10.1527/tjsai.27.1

DO - 10.1527/tjsai.27.1

M3 - Article

VL - 27

SP - 1

EP - 9

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 1

ER -