Answers are grounded in this paper and cite their sources.
Networking websites such as LinkedIn have now become rich sources of data that represent real world career con- nections. Unraveling the underlying community structure of such websites is critical in many domains, including recruitment, organizational analysis, and professional networking. In this work, the authors utilize graph theo- retical community detection techniques to study LinkedIn professional network data. nodes denote the LinkedIn members, and links denote the professional relationships among these members. To create an edge weight for this graph, three metrics of similarity were used: location, profession (using Jaccard similarity index) and age group. There are two algorithms utilized to detect communities: Louvain algorithm and Girvan-Newman algorithm. Some of the graph measures calculated include betweenness centrality, clustering coefficient, density, and mod- ularity. This experiment is conducted on the dataset containing 148 hand curated LinkedIn profiles. The result produced by Louvain algorithm shows 6 distinct communities in the network, with a modularity score of 0.508 that indicates high modularity in the network. On the other hand, Girvan-Newman algorithm did not perform well with the current dataset. It was found that professional role is the most important variable that influences community detection. Betweenness centrality is employed in detecting five important bridge professionals. the above mentioned study shows that graph theory approaches can be effectively used for investigating the underly- ing structures in professional social networks. The findings of this experiment will add value to the field of social network analysis in terms of the structural clustering.
No takes yet. Share an insight, caveat, or question.
Sakshi Tripathi (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: