Where you go reveals who you know: Analyzing social ties from millions of footprints

研究成果: Conference contribution

11 引文 (Scopus)

摘要

This paper aims to investigate how the geographical footprints of users correlate to their social ties. While conventional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, almost all of the user pairs with friendships had never met geographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to characterize the direct linkages between users through their spatial co-locations while the second is to capture the indirect linkages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70% accuracy) of detecting social ties solely from user footprints.

原文English
主出版物標題CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management
發行者Association for Computing Machinery
頁面1839-1842
頁數4
ISBN(電子)9781450337946
DOIs
出版狀態Published - 2015 十月 17
事件24th ACM International Conference on Information and Knowledge Management, CIKM 2015 - Melbourne, Australia
持續時間: 2015 十月 192015 十月 23

出版系列

名字International Conference on Information and Knowledge Management, Proceedings
19-23-Oct-2015

Other

Other24th ACM International Conference on Information and Knowledge Management, CIKM 2015
國家Australia
城市Melbourne
期間15-10-1915-10-23

指紋

Social ties
Co-location
Linkage
Experiment
Correlates
Graph
Friendship
Geography
Predictability
Wisdom

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Business, Management and Accounting(all)

引用此文

Hsieh, H. P., Yan, R., & Li, C. T. (2015). Where you go reveals who you know: Analyzing social ties from millions of footprints. 於 CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management (頁 1839-1842). (International Conference on Information and Knowledge Management, Proceedings; 卷 19-23-Oct-2015). Association for Computing Machinery. https://doi.org/10.1145/2806416.2806653
Hsieh, Hsun Ping ; Yan, Rui ; Li, Cheng Te. / Where you go reveals who you know : Analyzing social ties from millions of footprints. CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2015. 頁 1839-1842 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{5d237cc431ca424294fa1ece2b50e9ac,
title = "Where you go reveals who you know: Analyzing social ties from millions of footprints",
abstract = "This paper aims to investigate how the geographical footprints of users correlate to their social ties. While conventional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, almost all of the user pairs with friendships had never met geographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to characterize the direct linkages between users through their spatial co-locations while the second is to capture the indirect linkages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70{\%} accuracy) of detecting social ties solely from user footprints.",
author = "Hsieh, {Hsun Ping} and Rui Yan and Li, {Cheng Te}",
year = "2015",
month = "10",
day = "17",
doi = "10.1145/2806416.2806653",
language = "English",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "1839--1842",
booktitle = "CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management",

}

Hsieh, HP, Yan, R & Li, CT 2015, Where you go reveals who you know: Analyzing social ties from millions of footprints. 於 CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, 卷 19-23-Oct-2015, Association for Computing Machinery, 頁 1839-1842, 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, Australia, 15-10-19. https://doi.org/10.1145/2806416.2806653

Where you go reveals who you know : Analyzing social ties from millions of footprints. / Hsieh, Hsun Ping; Yan, Rui; Li, Cheng Te.

CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2015. p. 1839-1842 (International Conference on Information and Knowledge Management, Proceedings; 卷 19-23-Oct-2015).

研究成果: Conference contribution

TY - GEN

T1 - Where you go reveals who you know

T2 - Analyzing social ties from millions of footprints

AU - Hsieh, Hsun Ping

AU - Yan, Rui

AU - Li, Cheng Te

PY - 2015/10/17

Y1 - 2015/10/17

N2 - This paper aims to investigate how the geographical footprints of users correlate to their social ties. While conventional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, almost all of the user pairs with friendships had never met geographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to characterize the direct linkages between users through their spatial co-locations while the second is to capture the indirect linkages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70% accuracy) of detecting social ties solely from user footprints.

AB - This paper aims to investigate how the geographical footprints of users correlate to their social ties. While conventional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, almost all of the user pairs with friendships had never met geographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to characterize the direct linkages between users through their spatial co-locations while the second is to capture the indirect linkages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70% accuracy) of detecting social ties solely from user footprints.

UR - http://www.scopus.com/inward/record.url?scp=84958280866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958280866&partnerID=8YFLogxK

U2 - 10.1145/2806416.2806653

DO - 10.1145/2806416.2806653

M3 - Conference contribution

AN - SCOPUS:84958280866

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 1839

EP - 1842

BT - CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -

Hsieh HP, Yan R, Li CT. Where you go reveals who you know: Analyzing social ties from millions of footprints. 於 CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2015. p. 1839-1842. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2806416.2806653