Robust features of trust in social networks

Zoheb Hassan Borbora, Muhammad Aurangzeb Ahmad, Jehwan Oh, Karen Zita Haigh, Jaideep Srivastava, Zhen Wen

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

We identify robust features of trust in social networks; these are features which are discriminating yet uncorrelated and can potentially be used to predict trust formation between agents in other social networks. The features we investigate are based on an agent’s individual properties as well as those based on the agent’s location within the network. In addition, we analyze features which take into account the agent’s participation in other social interactions within the same network. Three datasets were used in our study—Sony Online Entertainment’s EverQuest II game dataset, a large email network with sentiments and the publicly available Epinions dataset. The first dataset captures activities from a complex persistent game environment characterized by several types of in-game social interactions, whereas the second dataset has anonymized information about people’s email and instant messaging communication. We formulate the problem as one of the link predictions, intranetwork and internetwork, in social networks. We first build machine learning models and then perform an ablation study to identify robust features of trust. Results indicate that shared skills and interests between two agents, their level of activity and level of expertise are the top three predictors of trust in a social network. Furthermore, if only network topology information were available, then an agent’s propensity to connect or communicate, the cosine similarity between two agents and shortest distance between them are found to be the top three predictors of trust. In our study, we have identified the generic characteristics of the networks used as well as the features investigated so that they can be used as guidelines for studying the problem of predicting trust formation in other social networks.

Original languageEnglish
Pages (from-to)981-999
Number of pages19
JournalSocial Network Analysis and Mining
Volume3
Issue number4
DOIs
Publication statusPublished - 1 Jan 2013
Externally publishedYes

Fingerprint

social network
Electronic mail
interaction
available information
entertainment
expertise
Ablation
Learning systems
participation
communication
Topology
learning
Communication

Keywords

  • Ablation study
  • Feature selection
  • Link prediction
  • Trust formation

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Information Systems
  • Communication
  • Media Technology

Cite this

Robust features of trust in social networks. / Borbora, Zoheb Hassan; Ahmad, Muhammad Aurangzeb; Oh, Jehwan; Haigh, Karen Zita; Srivastava, Jaideep; Wen, Zhen.

In: Social Network Analysis and Mining, Vol. 3, No. 4, 01.01.2013, p. 981-999.

Research output: Contribution to journalArticle

Borbora, ZH, Ahmad, MA, Oh, J, Haigh, KZ, Srivastava, J & Wen, Z 2013, 'Robust features of trust in social networks', Social Network Analysis and Mining, vol. 3, no. 4, pp. 981-999. https://doi.org/10.1007/s13278-013-0136-6
Borbora, Zoheb Hassan ; Ahmad, Muhammad Aurangzeb ; Oh, Jehwan ; Haigh, Karen Zita ; Srivastava, Jaideep ; Wen, Zhen. / Robust features of trust in social networks. In: Social Network Analysis and Mining. 2013 ; Vol. 3, No. 4. pp. 981-999.
@article{fe5ff3a9c11c4da1a76055eec8ab9b44,
title = "Robust features of trust in social networks",
abstract = "We identify robust features of trust in social networks; these are features which are discriminating yet uncorrelated and can potentially be used to predict trust formation between agents in other social networks. The features we investigate are based on an agent’s individual properties as well as those based on the agent’s location within the network. In addition, we analyze features which take into account the agent’s participation in other social interactions within the same network. Three datasets were used in our study—Sony Online Entertainment’s EverQuest II game dataset, a large email network with sentiments and the publicly available Epinions dataset. The first dataset captures activities from a complex persistent game environment characterized by several types of in-game social interactions, whereas the second dataset has anonymized information about people’s email and instant messaging communication. We formulate the problem as one of the link predictions, intranetwork and internetwork, in social networks. We first build machine learning models and then perform an ablation study to identify robust features of trust. Results indicate that shared skills and interests between two agents, their level of activity and level of expertise are the top three predictors of trust in a social network. Furthermore, if only network topology information were available, then an agent’s propensity to connect or communicate, the cosine similarity between two agents and shortest distance between them are found to be the top three predictors of trust. In our study, we have identified the generic characteristics of the networks used as well as the features investigated so that they can be used as guidelines for studying the problem of predicting trust formation in other social networks.",
keywords = "Ablation study, Feature selection, Link prediction, Trust formation",
author = "Borbora, {Zoheb Hassan} and Ahmad, {Muhammad Aurangzeb} and Jehwan Oh and Haigh, {Karen Zita} and Jaideep Srivastava and Zhen Wen",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/s13278-013-0136-6",
language = "English",
volume = "3",
pages = "981--999",
journal = "Social Network Analysis and Mining",
issn = "1869-5450",
publisher = "Springer Wien",
number = "4",

}

TY - JOUR

T1 - Robust features of trust in social networks

AU - Borbora, Zoheb Hassan

AU - Ahmad, Muhammad Aurangzeb

AU - Oh, Jehwan

AU - Haigh, Karen Zita

AU - Srivastava, Jaideep

AU - Wen, Zhen

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We identify robust features of trust in social networks; these are features which are discriminating yet uncorrelated and can potentially be used to predict trust formation between agents in other social networks. The features we investigate are based on an agent’s individual properties as well as those based on the agent’s location within the network. In addition, we analyze features which take into account the agent’s participation in other social interactions within the same network. Three datasets were used in our study—Sony Online Entertainment’s EverQuest II game dataset, a large email network with sentiments and the publicly available Epinions dataset. The first dataset captures activities from a complex persistent game environment characterized by several types of in-game social interactions, whereas the second dataset has anonymized information about people’s email and instant messaging communication. We formulate the problem as one of the link predictions, intranetwork and internetwork, in social networks. We first build machine learning models and then perform an ablation study to identify robust features of trust. Results indicate that shared skills and interests between two agents, their level of activity and level of expertise are the top three predictors of trust in a social network. Furthermore, if only network topology information were available, then an agent’s propensity to connect or communicate, the cosine similarity between two agents and shortest distance between them are found to be the top three predictors of trust. In our study, we have identified the generic characteristics of the networks used as well as the features investigated so that they can be used as guidelines for studying the problem of predicting trust formation in other social networks.

AB - We identify robust features of trust in social networks; these are features which are discriminating yet uncorrelated and can potentially be used to predict trust formation between agents in other social networks. The features we investigate are based on an agent’s individual properties as well as those based on the agent’s location within the network. In addition, we analyze features which take into account the agent’s participation in other social interactions within the same network. Three datasets were used in our study—Sony Online Entertainment’s EverQuest II game dataset, a large email network with sentiments and the publicly available Epinions dataset. The first dataset captures activities from a complex persistent game environment characterized by several types of in-game social interactions, whereas the second dataset has anonymized information about people’s email and instant messaging communication. We formulate the problem as one of the link predictions, intranetwork and internetwork, in social networks. We first build machine learning models and then perform an ablation study to identify robust features of trust. Results indicate that shared skills and interests between two agents, their level of activity and level of expertise are the top three predictors of trust in a social network. Furthermore, if only network topology information were available, then an agent’s propensity to connect or communicate, the cosine similarity between two agents and shortest distance between them are found to be the top three predictors of trust. In our study, we have identified the generic characteristics of the networks used as well as the features investigated so that they can be used as guidelines for studying the problem of predicting trust formation in other social networks.

KW - Ablation study

KW - Feature selection

KW - Link prediction

KW - Trust formation

UR - http://www.scopus.com/inward/record.url?scp=84945569463&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945569463&partnerID=8YFLogxK

U2 - 10.1007/s13278-013-0136-6

DO - 10.1007/s13278-013-0136-6

M3 - Article

VL - 3

SP - 981

EP - 999

JO - Social Network Analysis and Mining

JF - Social Network Analysis and Mining

SN - 1869-5450

IS - 4

ER -