Community detection in social networks using logic-based probabilistic programming
by Ahmed Ibrahem Hafez; Eiman Tamah Al-Shammari; Aboul Ella Hassanien; Aly A. Fahmy
International Journal of Social Network Mining (IJSNM), Vol. 2, No. 2, 2015

Abstract: Community detection in complex networks has attracted a lot of attention in recent years. Communities play special roles in the structure-function relationship; therefore, detecting communities can be a way to identify substructures that could correspond to important functions. Social networks can be formalised by a generative process in which interactions between actors are generated based on some assumptions, i.e., a model with some parameters. Based on that idea, a probabilistic inference technique can be used to infer the community structure of the network. We propose a generative model to describe how network interactions are generated and show the use of a logic-based probabilistic modelling technique such as PRISM, to solve the community detection problem. The proposed model works well with directed and undirected networks, and with weighted and un-weighted networks. We use the deterministic annealing expectation maximisation algorithm in the learning process, which prove to yield a very promising result when is applied to the community detection problem.

Online publication date: Thu, 08-Oct-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Social Network Mining (IJSNM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com