Exploring the significance of human mobility patterns in social link prediction

Handle URI:
http://hdl.handle.net/10754/564840
Title:
Exploring the significance of human mobility patterns in social link prediction
Authors:
Alharbi, Basma Mohammed ( 0000-0001-5399-2320 ) ; Zhang, Xiangliang ( 0000-0002-3574-5665 )
Abstract:
Link prediction is a fundamental task in social networks. Recently, emphasis has been placed on forecasting new social ties using user mobility patterns, e.g., investigating physical and semantic co-locations for new proximity measure. This paper explores the effect of in-depth mobility patterns. Specifically, we study individuals' movement behavior, and quantify mobility on the basis of trip frequency, travel purpose and transportation mode. Our hybrid link prediction model is composed of two modules. The first module extracts mobility patterns, including travel purpose and mode, from raw trajectory data. The second module employs the extracted patterns for link prediction. We evaluate our method on two real data sets, GeoLife [15] and Reality Mining [5]. Experimental results show that our hybrid model significantly improves the accuracy of social link prediction, when comparing to primary topology-based solutions. Copyright 2014 ACM.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Machine Intelligence & kNowledge Engineering Lab
Publisher:
Association for Computing Machinery (ACM)
Journal:
Proceedings of the 29th Annual ACM Symposium on Applied Computing - SAC '14
Conference/Event name:
29th Annual ACM Symposium on Applied Computing, SAC 2014
Issue Date:
2014
DOI:
10.1145/2554850.2554918
Type:
Conference Paper
ISBN:
9781450324694
Appears in Collections:
Conference Papers; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorAlharbi, Basma Mohammeden
dc.contributor.authorZhang, Xiangliangen
dc.date.accessioned2015-08-04T07:22:43Zen
dc.date.available2015-08-04T07:22:43Zen
dc.date.issued2014en
dc.identifier.isbn9781450324694en
dc.identifier.doi10.1145/2554850.2554918en
dc.identifier.urihttp://hdl.handle.net/10754/564840en
dc.description.abstractLink prediction is a fundamental task in social networks. Recently, emphasis has been placed on forecasting new social ties using user mobility patterns, e.g., investigating physical and semantic co-locations for new proximity measure. This paper explores the effect of in-depth mobility patterns. Specifically, we study individuals' movement behavior, and quantify mobility on the basis of trip frequency, travel purpose and transportation mode. Our hybrid link prediction model is composed of two modules. The first module extracts mobility patterns, including travel purpose and mode, from raw trajectory data. The second module employs the extracted patterns for link prediction. We evaluate our method on two real data sets, GeoLife [15] and Reality Mining [5]. Experimental results show that our hybrid model significantly improves the accuracy of social link prediction, when comparing to primary topology-based solutions. Copyright 2014 ACM.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.subjectCall detail recordsen
dc.subjectLink predictionen
dc.subjectMobility patternen
dc.subjectSocial networksen
dc.subjectSocial tiesen
dc.subjectTransportation modeen
dc.titleExploring the significance of human mobility patterns in social link predictionen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentMachine Intelligence & kNowledge Engineering Laben
dc.identifier.journalProceedings of the 29th Annual ACM Symposium on Applied Computing - SAC '14en
dc.conference.date24 March 2014 through 28 March 2014en
dc.conference.name29th Annual ACM Symposium on Applied Computing, SAC 2014en
dc.conference.locationGyeongjuen
kaust.authorZhang, Xiangliangen
kaust.authorAlharbi, Basma Mohammeden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.