Predicting links in ego-networks using temporal information

Research output: Contribution to journalArticle

10 Downloads (Pure)

Abstract

Link prediction appears as a central problem of network science, as it calls for unfolding the mechanisms that govern the micro-dynamics of the network. In this work, we are interested in ego-networks, that is the mere information of interactions of a node to its neighbors, in the context of social relationships. As the structural information is very poor, we rely on another source of information to predict links among egos’ neighbors: the timing of interactions. We define several features to capture different kinds of temporal information and apply machine learning methods to combine these various features and improve the quality of the prediction. We demonstrate the efficiency of this temporal approach on a cellphone interaction dataset, pointing out features which prove themselves to perform well in this context, in particular the temporal profile of interactions and elapsed time between contacts.

Original languageEnglish
Article number1
Number of pages16
JournalEPJ Data Science
Volume5
Issue number1
DOIs
Publication statusPublished - 2016

Fingerprint

Interaction
Learning systems
Prediction
Unfolding
Timing
Machine Learning
Contact
Predict
Vertex of a graph
Demonstrate
Context
Relationships
Profile

Keywords

  • Ego networks
  • Learning-to-rank
  • Link prediction
  • Social networks

Cite this

@article{2dd84bfa28bc4de88b0762c829745575,
title = "Predicting links in ego-networks using temporal information",
abstract = "Link prediction appears as a central problem of network science, as it calls for unfolding the mechanisms that govern the micro-dynamics of the network. In this work, we are interested in ego-networks, that is the mere information of interactions of a node to its neighbors, in the context of social relationships. As the structural information is very poor, we rely on another source of information to predict links among egos’ neighbors: the timing of interactions. We define several features to capture different kinds of temporal information and apply machine learning methods to combine these various features and improve the quality of the prediction. We demonstrate the efficiency of this temporal approach on a cellphone interaction dataset, pointing out features which prove themselves to perform well in this context, in particular the temporal profile of interactions and elapsed time between contacts.",
keywords = "Ego networks, Learning-to-rank, Link prediction, Social networks",
author = "Lionel Tabourier and Libert, {Anne Sophie} and Renaud Lambiotte",
year = "2016",
doi = "10.1140/epjds/s13688-015-0062-0",
language = "English",
volume = "5",
journal = "EPJ Data Science",
issn = "2193-1127",
publisher = "Springer Science + Business Media",
number = "1",

}

TY - JOUR

T1 - Predicting links in ego-networks using temporal information

AU - Tabourier, Lionel

AU - Libert, Anne Sophie

AU - Lambiotte, Renaud

PY - 2016

Y1 - 2016

N2 - Link prediction appears as a central problem of network science, as it calls for unfolding the mechanisms that govern the micro-dynamics of the network. In this work, we are interested in ego-networks, that is the mere information of interactions of a node to its neighbors, in the context of social relationships. As the structural information is very poor, we rely on another source of information to predict links among egos’ neighbors: the timing of interactions. We define several features to capture different kinds of temporal information and apply machine learning methods to combine these various features and improve the quality of the prediction. We demonstrate the efficiency of this temporal approach on a cellphone interaction dataset, pointing out features which prove themselves to perform well in this context, in particular the temporal profile of interactions and elapsed time between contacts.

AB - Link prediction appears as a central problem of network science, as it calls for unfolding the mechanisms that govern the micro-dynamics of the network. In this work, we are interested in ego-networks, that is the mere information of interactions of a node to its neighbors, in the context of social relationships. As the structural information is very poor, we rely on another source of information to predict links among egos’ neighbors: the timing of interactions. We define several features to capture different kinds of temporal information and apply machine learning methods to combine these various features and improve the quality of the prediction. We demonstrate the efficiency of this temporal approach on a cellphone interaction dataset, pointing out features which prove themselves to perform well in this context, in particular the temporal profile of interactions and elapsed time between contacts.

KW - Ego networks

KW - Learning-to-rank

KW - Link prediction

KW - Social networks

UR - http://www.scopus.com/inward/record.url?scp=85007212152&partnerID=8YFLogxK

U2 - 10.1140/epjds/s13688-015-0062-0

DO - 10.1140/epjds/s13688-015-0062-0

M3 - Article

VL - 5

JO - EPJ Data Science

JF - EPJ Data Science

SN - 2193-1127

IS - 1

M1 - 1

ER -