Publication Type

Encyclopaedia

Version

acceptedVersion

Publication Date

1-2018

Abstract

In this entry, we mine collaboration patterns from a large software developer network (Surian et al. 2010). We consider high- and low-level patterns. High-level patterns correspond to various network-level statistics that we observe to hold in this network. Low-level patterns are topological subgraph patterns that are frequently observed among developers collaborating in the network. Mining topological subgraph patterns are difficult as it is an NP-hard problem. To address this issue, we use a combination of frequent subgraph mining and graph matching by leveraging the power law property exhibited by a large collaboration graph. The technique is applicable to any software developer network that could be represented as a large graph. As a case study, we experiment with a developer collaboration network extracted from SourceForge.Net, which is the most popular open-source software portal.

Keywords

Collaboration patterns, Developer collaboration network, Graph pattern mining

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

Encyclopedia of social network analysis and mining

Editor

R. Alhajj, & J. Rokne

First Page

224

Last Page

229

ISBN

9781493971312

Identifier

10.1007/978-1-4939-7131-2_292

Publisher

Springer

City or Country

Cham

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1007/978-1-4939-7131-2_292

Download

Share

COinS