Abstract

Inferring unknown social trust relations attracts increasing attention in recent years. However, social trust, as a social concept, is intrinsically dynamic, and exploiting temporal dynamics provides challenges and opportunities for social trust prediction. In this paper, we investigate social trust prediction by exploiting temporal dynamics. In particular, we model the dynamics of user preferences in two principled ways. The first one focuses on temporal weight; the second one targets temporal smoothness. By incorporating these two types of temporal dynamics into traditional matrix factorization based social trust prediction model, two extended social trust prediction models are proposed and the corresponding algorithms to solve the models are designed too. We conduct experiments on a real-world dataset and the results demonstrate the effectiveness of our proposed new models. Further experiments are also conducted to understand the importance of temporal dynamics in social trust prediction.

Original languageEnglish (US)
Pages (from-to)369-378
Number of pages10
JournalWuhan University Journal of Natural Sciences
Volume19
Issue number5
DOIs
StatePublished - Oct 1 2014

Fingerprint

Factorization
Experiments

Keywords

  • social network
  • temporal dynamics
  • trust prediction

ASJC Scopus subject areas

  • General

Cite this

Temporal dynamics in social trust prediction. / Cai, Guoyong; Lv, Rui; Tang, Jiliang; Liu, Huan.

In: Wuhan University Journal of Natural Sciences, Vol. 19, No. 5, 01.10.2014, p. 369-378.

Research output: Contribution to journalArticle

Cai, Guoyong ; Lv, Rui ; Tang, Jiliang ; Liu, Huan. / Temporal dynamics in social trust prediction. In: Wuhan University Journal of Natural Sciences. 2014 ; Vol. 19, No. 5. pp. 369-378.
@article{f936a9ee627943588b3689ccbc202383,
title = "Temporal dynamics in social trust prediction",
abstract = "Inferring unknown social trust relations attracts increasing attention in recent years. However, social trust, as a social concept, is intrinsically dynamic, and exploiting temporal dynamics provides challenges and opportunities for social trust prediction. In this paper, we investigate social trust prediction by exploiting temporal dynamics. In particular, we model the dynamics of user preferences in two principled ways. The first one focuses on temporal weight; the second one targets temporal smoothness. By incorporating these two types of temporal dynamics into traditional matrix factorization based social trust prediction model, two extended social trust prediction models are proposed and the corresponding algorithms to solve the models are designed too. We conduct experiments on a real-world dataset and the results demonstrate the effectiveness of our proposed new models. Further experiments are also conducted to understand the importance of temporal dynamics in social trust prediction.",
keywords = "social network, temporal dynamics, trust prediction",
author = "Guoyong Cai and Rui Lv and Jiliang Tang and Huan Liu",
year = "2014",
month = "10",
day = "1",
doi = "10.1007/s11859-014-1027-z",
language = "English (US)",
volume = "19",
pages = "369--378",
journal = "Wuhan University Journal of Natural Sciences",
issn = "1007-1202",
publisher = "Wuhan University",
number = "5",

}

TY - JOUR

T1 - Temporal dynamics in social trust prediction

AU - Cai, Guoyong

AU - Lv, Rui

AU - Tang, Jiliang

AU - Liu, Huan

PY - 2014/10/1

Y1 - 2014/10/1

N2 - Inferring unknown social trust relations attracts increasing attention in recent years. However, social trust, as a social concept, is intrinsically dynamic, and exploiting temporal dynamics provides challenges and opportunities for social trust prediction. In this paper, we investigate social trust prediction by exploiting temporal dynamics. In particular, we model the dynamics of user preferences in two principled ways. The first one focuses on temporal weight; the second one targets temporal smoothness. By incorporating these two types of temporal dynamics into traditional matrix factorization based social trust prediction model, two extended social trust prediction models are proposed and the corresponding algorithms to solve the models are designed too. We conduct experiments on a real-world dataset and the results demonstrate the effectiveness of our proposed new models. Further experiments are also conducted to understand the importance of temporal dynamics in social trust prediction.

AB - Inferring unknown social trust relations attracts increasing attention in recent years. However, social trust, as a social concept, is intrinsically dynamic, and exploiting temporal dynamics provides challenges and opportunities for social trust prediction. In this paper, we investigate social trust prediction by exploiting temporal dynamics. In particular, we model the dynamics of user preferences in two principled ways. The first one focuses on temporal weight; the second one targets temporal smoothness. By incorporating these two types of temporal dynamics into traditional matrix factorization based social trust prediction model, two extended social trust prediction models are proposed and the corresponding algorithms to solve the models are designed too. We conduct experiments on a real-world dataset and the results demonstrate the effectiveness of our proposed new models. Further experiments are also conducted to understand the importance of temporal dynamics in social trust prediction.

KW - social network

KW - temporal dynamics

KW - trust prediction

UR - http://www.scopus.com/inward/record.url?scp=84919915756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919915756&partnerID=8YFLogxK

U2 - 10.1007/s11859-014-1027-z

DO - 10.1007/s11859-014-1027-z

M3 - Article

AN - SCOPUS:84919915756

VL - 19

SP - 369

EP - 378

JO - Wuhan University Journal of Natural Sciences

JF - Wuhan University Journal of Natural Sciences

SN - 1007-1202

IS - 5

ER -