From foursquare to my square: Learning check-in behavior from multiple sources

Eric Malmi; Trinh Minh Tri Do; Daniel Gatica-Perez

From foursquare to my square: Learning check-in behavior from multiple sources

Eric Malmi, Trinh Minh Tri Do, Daniel Gatica-Perez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

6 Citations (Scopus)

Abstract

Location-based services often use only a single mobility data source, which typically will be scarce for any new user when the system starts out. We propose a transfer learning method to characterize the temporal distribution of places of individuals by using an external, additional, large-scale check-in data set such as Foursquare data. The method is applied to the next place prediction problem, and we show that the incorporation of additional data through the proposed method improves the prediction accuracy when there is a limited amount of prior data.

Original language	English
Title of host publication	Proceedings of the 7th International Conference on Weblogs and Social Media, ICWSM 2013
Publisher	AAAI PRESS
Pages	701-704
Number of pages	4
Publication status	Published - 2013
MoE publication type	A4 Article in a conference publication
Event	International AAAI Conference on Weblogs and Social Media - Cambridge, United States Duration: 8 Jul 2013 → 11 Jul 2013 Conference number: 7

Conference

Conference	International AAAI Conference on Weblogs and Social Media
Abbreviated title	ICWSM
Country	United States
City	Cambridge
Period	08/07/2013 → 11/07/2013

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'From foursquare to my square: Learning check-in behavior from multiple sources'. Together they form a unique fingerprint.

Cite this

@inproceedings{f647a019b4024a05a067351c0691a7c2,

title = "From foursquare to my square: Learning check-in behavior from multiple sources",

abstract = "Location-based services often use only a single mobility data source, which typically will be scarce for any new user when the system starts out. We propose a transfer learning method to characterize the temporal distribution of places of individuals by using an external, additional, large-scale check-in data set such as Foursquare data. The method is applied to the next place prediction problem, and we show that the incorporation of additional data through the proposed method improves the prediction accuracy when there is a limited amount of prior data.",

author = "Eric Malmi and Do, {Trinh Minh Tri} and Daniel Gatica-Perez",

year = "2013",

language = "English",

pages = "701--704",

booktitle = "Proceedings of the 7th International Conference on Weblogs and Social Media, ICWSM 2013",

publisher = "AAAI PRESS",

note = "International AAAI Conference on Weblogs and Social Media, ICWSM ; Conference date: 08-07-2013 Through 11-07-2013",

}

From foursquare to my square : Learning check-in behavior from multiple sources. / Malmi, Eric; Do, Trinh Minh Tri; Gatica-Perez, Daniel.

Proceedings of the 7th International Conference on Weblogs and Social Media, ICWSM 2013. AAAI PRESS, 2013. p. 701-704.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - From foursquare to my square

T2 - International AAAI Conference on Weblogs and Social Media

AU - Malmi, Eric

AU - Do, Trinh Minh Tri

AU - Gatica-Perez, Daniel

N1 - Conference code: 7

PY - 2013

Y1 - 2013

N2 - Location-based services often use only a single mobility data source, which typically will be scarce for any new user when the system starts out. We propose a transfer learning method to characterize the temporal distribution of places of individuals by using an external, additional, large-scale check-in data set such as Foursquare data. The method is applied to the next place prediction problem, and we show that the incorporation of additional data through the proposed method improves the prediction accuracy when there is a limited amount of prior data.

AB - Location-based services often use only a single mobility data source, which typically will be scarce for any new user when the system starts out. We propose a transfer learning method to characterize the temporal distribution of places of individuals by using an external, additional, large-scale check-in data set such as Foursquare data. The method is applied to the next place prediction problem, and we show that the incorporation of additional data through the proposed method improves the prediction accuracy when there is a limited amount of prior data.

UR - http://www.scopus.com/inward/record.url?scp=84900432845&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84900432845

SP - 701

EP - 704

BT - Proceedings of the 7th International Conference on Weblogs and Social Media, ICWSM 2013

PB - AAAI PRESS

Y2 - 8 July 2013 through 11 July 2013

ER -