A Comparative Analysis of Community Detection Agglomerative Technique Algorithms and Metrics on Citation Network

Abstract

Social Network Analysis is a discipline that represents social relationships as a network of nodes and edges. The construction of social network with clusters will contribute in sharing the common characteristics or behaviour of a group. Partitioning the graph into modules is said to be a community. Communities are meant to symbolize actual social groups that share common characteristics. Citation network is one of the social networks with directed graphs where one paper will cite another paper and so on. Citation networks will assist the researcher in choosing research directions and evaluating research impacts. By constructing the citation networks with communities will direct the user to identify the similarity of documents which are interrelated to one or more domains. This paper introduces the agglomerative technique algorithms and metrics to a directed graph which determines the most influential nodes and group of similar nodes. The two stages required to construct the communities are how to generate network with communities and how to quantify the network performance. The strength and a quality of a network is quantified in terms of metrics like modularity, normalized mutual information (NMI), betweenness centrality, and F-Measure. The suitable community detection techniques and metrics for a citation graph were introduced in this paper. In the field of community detection, it is common practice to categorize algorithms according to the mathematical techniques they employ, and then compare them on benchmark graphs featuring a particular type of assortative community structure. The algorithms are applied for a sample citation sub data is extracted from DBLP, ACM, MAG and some additional sources which is taken from and consists of 101 nodes (nc) with 621 edges € and formed 64 communities. The key attributes in dataset are id, title, abstract, references SLM uses local optimisation and scalability to improve community detection in complicated networks. Unlike traditional methods, the proposed LS-SLM algorithm is identified that the modularity is increased by 12.65%, NMI increased by 2.31%, betweenness centrality by 3.18% and F-Score by 4.05%. The SLM algorithm outperforms existing methods in finding significant and well-defined communities, making it a promising community detection breakthrough.