Extracting Rankings for Spatial Keyword Queries from GPS Data

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Resumé

Studies suggest that many search engine queries have local intent. We consider the evaluation of ranking functions important for such queries. The key challenge is to be able to determine the “best” ranking for a query, as this enables evaluation of the results of ranking functions. We propose a model that synthesizes a ranking of points of interest (PoI) for a given query using historical trips extracted from GPS data. To extract trips, we propose a novel PoI assignment method that makes use of distances and temporal information. We also propose a PageRank-based smoothing method to be able to answer queries for regions that are not covered well by trips. We report experimental results on a large GPS dataset that show that the proposed model is capable of capturing the visits of users to PoIs and of synthesizing rankings.
OriginalsprogEngelsk
TitelProgress in Location Based Services 2018
Antal sider22
ForlagSpringer
Publikationsdato2018
Sider173-194
ISBN (Trykt)978-3-319-71469-1
ISBN (Elektronisk)978-3-319-71470-7
DOI
StatusUdgivet - 2018
Begivenhed14th International Conference on Location Based Services - Zurich, Schweiz
Varighed: 15 jan. 201817 jan. 2018
http://lbs18.ethz.ch/

Konference

Konference14th International Conference on Location Based Services
LandSchweiz
ByZurich
Periode15/01/201817/01/2018
Internetadresse
NavnLecture notes in geoinformation and Cartography
ISSN1863-2246

Fingerprint

Global positioning system
Search engines

Citer dette

Keles, I., Jensen, C. S., & Saltenis, S. (2018). Extracting Rankings for Spatial Keyword Queries from GPS Data. I Progress in Location Based Services 2018 (s. 173-194). Springer. Lecture notes in geoinformation and Cartography https://doi.org/10.1007/978-3-319-71470-7_9
Keles, Ilkcan ; Jensen, Christian Søndergaard ; Saltenis, Simonas. / Extracting Rankings for Spatial Keyword Queries from GPS Data. Progress in Location Based Services 2018. Springer, 2018. s. 173-194 (Lecture notes in geoinformation and Cartography).
@inproceedings{4ba1664199f846ada4106c22a4b26a85,
title = "Extracting Rankings for Spatial Keyword Queries from GPS Data",
abstract = "Studies suggest that many search engine queries have local intent. We consider the evaluation of ranking functions important for such queries. The key challenge is to be able to determine the “best” ranking for a query, as this enables evaluation of the results of ranking functions. We propose a model that synthesizes a ranking of points of interest (PoI) for a given query using historical trips extracted from GPS data. To extract trips, we propose a novel PoI assignment method that makes use of distances and temporal information. We also propose a PageRank-based smoothing method to be able to answer queries for regions that are not covered well by trips. We report experimental results on a large GPS dataset that show that the proposed model is capable of capturing the visits of users to PoIs and of synthesizing rankings.",
author = "Ilkcan Keles and Jensen, {Christian S{\o}ndergaard} and Simonas Saltenis",
year = "2018",
doi = "10.1007/978-3-319-71470-7_9",
language = "English",
isbn = "978-3-319-71469-1",
pages = "173--194",
booktitle = "Progress in Location Based Services 2018",
publisher = "Springer",
address = "Germany",

}

Keles, I, Jensen, CS & Saltenis, S 2018, Extracting Rankings for Spatial Keyword Queries from GPS Data. i Progress in Location Based Services 2018. Springer, Lecture notes in geoinformation and Cartography, s. 173-194, Zurich, Schweiz, 15/01/2018. https://doi.org/10.1007/978-3-319-71470-7_9

Extracting Rankings for Spatial Keyword Queries from GPS Data. / Keles, Ilkcan; Jensen, Christian Søndergaard; Saltenis, Simonas.

Progress in Location Based Services 2018. Springer, 2018. s. 173-194 (Lecture notes in geoinformation and Cartography).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Extracting Rankings for Spatial Keyword Queries from GPS Data

AU - Keles, Ilkcan

AU - Jensen, Christian Søndergaard

AU - Saltenis, Simonas

PY - 2018

Y1 - 2018

N2 - Studies suggest that many search engine queries have local intent. We consider the evaluation of ranking functions important for such queries. The key challenge is to be able to determine the “best” ranking for a query, as this enables evaluation of the results of ranking functions. We propose a model that synthesizes a ranking of points of interest (PoI) for a given query using historical trips extracted from GPS data. To extract trips, we propose a novel PoI assignment method that makes use of distances and temporal information. We also propose a PageRank-based smoothing method to be able to answer queries for regions that are not covered well by trips. We report experimental results on a large GPS dataset that show that the proposed model is capable of capturing the visits of users to PoIs and of synthesizing rankings.

AB - Studies suggest that many search engine queries have local intent. We consider the evaluation of ranking functions important for such queries. The key challenge is to be able to determine the “best” ranking for a query, as this enables evaluation of the results of ranking functions. We propose a model that synthesizes a ranking of points of interest (PoI) for a given query using historical trips extracted from GPS data. To extract trips, we propose a novel PoI assignment method that makes use of distances and temporal information. We also propose a PageRank-based smoothing method to be able to answer queries for regions that are not covered well by trips. We report experimental results on a large GPS dataset that show that the proposed model is capable of capturing the visits of users to PoIs and of synthesizing rankings.

U2 - 10.1007/978-3-319-71470-7_9

DO - 10.1007/978-3-319-71470-7_9

M3 - Article in proceeding

SN - 978-3-319-71469-1

SP - 173

EP - 194

BT - Progress in Location Based Services 2018

PB - Springer

ER -

Keles I, Jensen CS, Saltenis S. Extracting Rankings for Spatial Keyword Queries from GPS Data. I Progress in Location Based Services 2018. Springer. 2018. s. 173-194. (Lecture notes in geoinformation and Cartography). https://doi.org/10.1007/978-3-319-71470-7_9