TY - JOUR
AU - Anamalamudi, Satish
AB - In complex networks, identifying influential nodes becomes critical as these networks emerge rapidly. Extensive studies have been carried out on intricate networks to comprehend diverse real-world networks, including transportation networks, facebook networks, animal social networks, etc. Centrality measures like degree, betweenness, closeness, and clustering centralities are used to find influential nodes, but these measures have limitations in implementation with large-scale networks. These centrality measures are classified into global and local centralities. Semi-local structures perform well compared to local and global centralities but efficient centrality for finding influential nodes remains a challenging issue in large-scale networks. To address this challenge, a Semi-Local Average Isolating Centrality (SAIC) metric is proposed that integrates semi-local and local information to identify important nodes in large networks, along with the relative change in average shortest path. Here, we consider extended neighborhood concept for selecting the nodes nearest neighbors along with the weighted edge policy to find the best influential nodes by using SAIC. Along with these, SAIC also consider isolated nodes which significantly impact the network connectedness by maximizing the number of connected components upon removal. As a result SAIC differentiates itself from other centrality metrics by employing a distributed approach to define semi-local structure and utilizing an efficient edge weighting policy. The analysis of SAIC has been performed on multiple real-time datasets using Kendall tau’s coefficient. Using the Susceptible-Infected-Recovered (SIR) and Independent Cascade(IC) models, the performance of SAIC has been examined to determine maximum information spread in comparison to the most recent metrics in some real-world datasets. Our proposed method SAIC performs better in terms of information spreading when compare with other exisiting methods, with an improvement ranging from 4.11% to 17.9%.
TI - Identifying influential nodes using semi local isolating centrality based on average shortest path
JF - Journal of Intelligent Information Systems
DO - 10.1007/s10844-025-00943-7
DA - 2025-04-28
UR - https://www.deepdyve.com/lp/springer-journals/identifying-influential-nodes-using-semi-local-isolating-centrality-4PmF0wYqlQ
SP - 1
EP - 30
VL - OnlineFirst
IS - 
DP - DeepDyve
ER -