An Approach to Mining Information From Telephone Graph Using Graph Mining Techniques

An Approach to Mining Information From Telephone Graph Using Graph Mining Techniques

Bapuji Rao, Sasmita Mishra, Sarojananda Mishra
DOI: 10.4018/978-1-5225-2814-2.ch003
(Individual Chapters)
No Current Special Offers


This chapter focuses on methods to study communication in a real world social network using the basic concepts of graph theory. The initial section of this chapter starts with a general introduction consisting of related literature and definitions towards understanding the basic concepts of graph mining and graph theory, defining a telephone graph and use of telephone graph for social contexts. The authors have proposed an algorithm for extracting different network provider's sub-graphs, weak and strong connected sub-graphs and extracting incoming and outgoing calls of subscribers which have direct application for studying the human behavior in telephone network. The authors have considered two examples. The authors have implemented the proposed algorithm in C++ programming language and obtained satisfactory results. Finally, the authors have included the snapshots of the output in the chapter to enhance the interest of the readers.
Chapter Preview

2. Modeling Telephone Network

The authors have observed that some of the real life social network examples include Telephone Networks, Email Networks, Authors Networks, Research Paper Networks, Collaboration Networks of Authors and Papers, Collaboration Networks of Teachers, Students, and Text Books (Girvan et. al., 2002). Such type of interactive and dynamic social network can easily be represented graphically using node and edge relationships. The authors have used matrix to represent Telephone Network in the computer’s memory. So as one can analyze on it by using graph mining techniques to get the desired and efficient knowledge easily and faster. The telephone networks representation and analysis has been explained in detail.

The nodes of the telephone network represent subscriber phone numbers, which are real world individuals. There is an edge between two nodes if a call has been made between those phones in some fixed period of time, such as last month, or for the last six months. The edges could be weighted by the number of calls made between these phones during the period. Communities in a telephone network will form from groups of people that communicate frequently: groups of friends, members of a club, or people working in the same organization. So as one can acquire the knowledge by extracting a particular service provider’s sub-graph, strong-connector sub-graph, weak-connector sub-graph, finding number of incoming calls and outgoing calls of a particular user for a particular period of time from a large telephone network.

Complete Chapter List

Search this Book: