A new metric to compare local community detection algorithms in social networks using geodesic distance

Sahar Bakhtar () and Hovhannes A. Harutyunyan
Additional contact information
Sahar Bakhtar: Concordia University
Hovhannes A. Harutyunyan: Concordia University

Journal of Combinatorial Optimization, 2022, vol. 44, issue 4, No 34, 2809-2831

Abstract: Abstract Community detection problem is a well-studied problem in social networks. One major question to this problem is how to evaluate different community detection algorithms. This issue is even more challenging in the problem of local community detection where only local information of communities is available. Normally, two community detection algorithms are compared by evaluating their resulted communities. In this regard, the most widely used technique to evaluate the quality of communities is to compare them with the ground-truth communities. However, for a large number of networks, the ground-truth communities are not known. As a result, it is necessary to have a comprehensive metric to evaluate the quality of communities. In this study, improving a local quality metric, a number of local community detection algorithms are compared through assessing their detected communities. Furthermore, using some small graphs as example communities, some drawbacks of a number of existing local metrics are discussed. Finally, according to the experimental results, it is illustrated that the local community detection algorithms are fairly compared using the proposed metric, GDM. It is also shown that the judgment of GDM is almost the same as that of F1-score, i.e. the metric which compares the community with its ground-truth community.

Keywords: Social networks; Community detection; Local community detection algorithms; Evaluation metrics (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10878-021-00794-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcomop:v:44:y:2022:i:4:d:10.1007_s10878-021-00794-2

Ordering information: This journal article can be ordered from
https://www.springer.com/journal/10878

DOI: 10.1007/s10878-021-00794-2

Access Statistics for this article

Journal of Combinatorial Optimization is currently edited by Thai, My T.

More articles in Journal of Combinatorial Optimization from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().