Abstract

Location-based social networks (LBSNs) have attracted an increasing number of users in recent years, resulting in large amounts of geographical and social data. Such LBSN data provide an unprecedented opportunity to study the human movement from their socio-spatial behavior, in order to improve location-based applications like location recommendation. As users can check-in at new places, traditional work on location prediction that relies on mining a user’s historical moving trajectories fails as it is not designed for the cold-start problem of recommending new check-ins. While previous work on LBSNs attempting to utilize a user’s social connections for location recommendation observed limited help from social network information. In this work, we propose to address the cold-start location recommendation problem by capturing the correlations between social networks and geographical distance on LBSNs with a geo-social correlation model. The experimental results on a real-world LBSN dataset demonstrate that our approach properly models the geo-social correlations of a user’s cold-start check-ins and significantly improves the location recommendation performance.

Original languageEnglish (US)
Pages (from-to)299-323
Number of pages25
JournalData Mining and Knowledge Discovery
Volume29
Issue number2
DOIs
StatePublished - 2014

Fingerprint

Trajectories

Keywords

  • Cold-start
  • Geo-social correlation
  • Location prediction
  • Location recommendation
  • Location-based social networks

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computer Networks and Communications

Cite this

Addressing the cold-start problem in location recommendation using geo-social correlations. / Gao, Huiji; Tang, Jiliang; Liu, Huan.

In: Data Mining and Knowledge Discovery, Vol. 29, No. 2, 2014, p. 299-323.

Research output: Contribution to journalArticle

@article{654d54091559469e805c9bb0d77a5435,
title = "Addressing the cold-start problem in location recommendation using geo-social correlations",
abstract = "Location-based social networks (LBSNs) have attracted an increasing number of users in recent years, resulting in large amounts of geographical and social data. Such LBSN data provide an unprecedented opportunity to study the human movement from their socio-spatial behavior, in order to improve location-based applications like location recommendation. As users can check-in at new places, traditional work on location prediction that relies on mining a user’s historical moving trajectories fails as it is not designed for the cold-start problem of recommending new check-ins. While previous work on LBSNs attempting to utilize a user’s social connections for location recommendation observed limited help from social network information. In this work, we propose to address the cold-start location recommendation problem by capturing the correlations between social networks and geographical distance on LBSNs with a geo-social correlation model. The experimental results on a real-world LBSN dataset demonstrate that our approach properly models the geo-social correlations of a user’s cold-start check-ins and significantly improves the location recommendation performance.",
keywords = "Cold-start, Geo-social correlation, Location prediction, Location recommendation, Location-based social networks",
author = "Huiji Gao and Jiliang Tang and Huan Liu",
year = "2014",
doi = "10.1007/s10618-014-0343-4",
language = "English (US)",
volume = "29",
pages = "299--323",
journal = "Data Mining and Knowledge Discovery",
issn = "1384-5810",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Addressing the cold-start problem in location recommendation using geo-social correlations

AU - Gao, Huiji

AU - Tang, Jiliang

AU - Liu, Huan

PY - 2014

Y1 - 2014

N2 - Location-based social networks (LBSNs) have attracted an increasing number of users in recent years, resulting in large amounts of geographical and social data. Such LBSN data provide an unprecedented opportunity to study the human movement from their socio-spatial behavior, in order to improve location-based applications like location recommendation. As users can check-in at new places, traditional work on location prediction that relies on mining a user’s historical moving trajectories fails as it is not designed for the cold-start problem of recommending new check-ins. While previous work on LBSNs attempting to utilize a user’s social connections for location recommendation observed limited help from social network information. In this work, we propose to address the cold-start location recommendation problem by capturing the correlations between social networks and geographical distance on LBSNs with a geo-social correlation model. The experimental results on a real-world LBSN dataset demonstrate that our approach properly models the geo-social correlations of a user’s cold-start check-ins and significantly improves the location recommendation performance.

AB - Location-based social networks (LBSNs) have attracted an increasing number of users in recent years, resulting in large amounts of geographical and social data. Such LBSN data provide an unprecedented opportunity to study the human movement from their socio-spatial behavior, in order to improve location-based applications like location recommendation. As users can check-in at new places, traditional work on location prediction that relies on mining a user’s historical moving trajectories fails as it is not designed for the cold-start problem of recommending new check-ins. While previous work on LBSNs attempting to utilize a user’s social connections for location recommendation observed limited help from social network information. In this work, we propose to address the cold-start location recommendation problem by capturing the correlations between social networks and geographical distance on LBSNs with a geo-social correlation model. The experimental results on a real-world LBSN dataset demonstrate that our approach properly models the geo-social correlations of a user’s cold-start check-ins and significantly improves the location recommendation performance.

KW - Cold-start

KW - Geo-social correlation

KW - Location prediction

KW - Location recommendation

KW - Location-based social networks

UR - http://www.scopus.com/inward/record.url?scp=84923215677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923215677&partnerID=8YFLogxK

U2 - 10.1007/s10618-014-0343-4

DO - 10.1007/s10618-014-0343-4

M3 - Article

AN - SCOPUS:84923215677

VL - 29

SP - 299

EP - 323

JO - Data Mining and Knowledge Discovery

JF - Data Mining and Knowledge Discovery

SN - 1384-5810

IS - 2

ER -