MCD: A modified community diversity approach for detecting influential nodes in social networks

Gupta, Aaryan; Khatri, Inder; Choudhry, Arjun; Kumar, Sanjay

doi:10.1007/s10844-023-00776-2

Cited by 7 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modified Community Diversity was designed by Gupta et al 27 using neighborhood information to avoid overlapping issues. The bridge nodes were identified using the community diversity score, and then, the extended community score was estimated to detect the node's distribution capability.…”

Section: Literature Reviewmentioning

confidence: 99%

HIKS: A K‐shell‐weighted hybrid approach method for detecting influential nodes in complex networks using possible edge weights

Seshu Chakravarthy,

Selvaraj

2024

Int J Communication

View full text Add to dashboard Cite

SummaryThe influential node in the network is the node that has a higher impact on network functioning compared to the other nodes. The influential node detection in the complex network is crucial for rumor containment, virus spreading, viral marketing, and so forth. The researchers designed several influential node detection methods; still, detecting community and influential node selection with minimal computational complexity by considering the relationship between the nodes is challenging. Hence, an optimal community detection along with the hybrid K‐shell decomposition method is introduced in this research. Initially, the optimal community from the complex network is identified to reduce the computation burden. For this, the Improved Dingo (IDingo) algorithm is introduced by hybridizing the hunting behavior of Dingo and the rough encircling behavior of Harris Hawk. After detecting the optimal community, the influential node identification is devised using the proposed hybrid K‐shell decomposition methods. The potential edge weights are considered while ranking the nodes. The performance of a proposed method is analyzed using six various datasets and accomplished the maximal cluster coefficient of 0.56578, 0.25674, 0.24022, 0.5968, 0.23419, and 0.10196 for Karate, Dolphins, C‐Elegance, Facebook, Gowalla, and Power Grid Dataset.

show abstract

Section: Literature Reviewmentioning

confidence: 99%