12,000

We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK

93%

93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > Evolving social network analysis: A case study ...
View graph of relations

« Back

Evolving social network analysis: A case study on mobile phone data

Research output: Contribution in Book/Report/ProceedingsPaper

Published

Publication date2012
Host publicationEvolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on
PublisherIEEE
Pages114-120
Number of pages7
ISBN (Electronic)978-1-4673-1726-9
ISBN (Print)978-1-4673-1728-3
Original languageEnglish

Abstract

Mobile phone data can provide rich information on human activities and their social relationships which are dynamic in nature. Analysis of such social networks emerging from phone calls of mobile users can be useful in many aspects. In this paper we report the methods and results from a case study on the analysis of a social network from mobile phone data. The analysis involves tracking the dynamics of the network, identifying key individuals and their close associates,
and identifying individuals having communication pattern similar to the key individuals. We introduce novel measures to quantify, the evolution in the network, significance of an individual, and social association of an individual. In order to
group individuals having similar communication pattern, we applied recently proposed online clustering approach called eClustering (evolving clustering) due to its adaptive nature and low computational overhead. The results show the pertinence of the proposed quantification measures to analysis of evolving social network.