×
Home Current Archive Editorial board
Instructions for papers
For Authors Aim & Scope Contact
Original scientific article

AN INFLUENCER NODE IDENTIFICATION USING HYBRID MACHINE LEARNING TECHNIQUES

By
CS. Saradha Orcid logo
CS. Saradha

Associate Professor in Computer Science, PSG College of Arts & Science , Coimbatore, Tamil Nadu , India

Abstract

Influential node detection in networks is vital in diverse applications, particularly with the online social networks (OSNs). Measures of centrality, traditional ones, fail to sufficiently describe the influence of nodes on complex and multilayered networks. This paper presents a novel hybrid method that combines traditional topological centrality metrics with machine learning to be able to detect influential nodes. The proposed approach applies degree, betweenness, closeness, eigenvector centrality, PageRank, and clustering coefficients as the characteristics of a Hybrid Random Forest classifier, which is improved with Gradient Boosting Decision Trees (RF-GBDT). The model is tested using the simulation based on the dynamics of interaction between influencers in a network. The findings show that the RF-GBDT approach is much more effective than conventional methods as it has an accuracy of 96.7%. The hybrid approach is better in detecting influential people, which is essential in maximizing brand marketing in the social media. The results indicate that topological characteristics and machine learning models can be used together to provide more accuracy in the detection of key players through OSN analysis. The implications that this methodology would have on targeted marketing, social media analytics, and online community development may be significant. Further investigation opportunities exist to develop the model further on the scalability in generalized network environments and to apply the model to larger social and professional network environments.

References

1.
Rashid Y, Bhat JI. Topological to deep learning era for identifying influencers in online social networks: a systematic review. Multimedia Tools and Applications. 2024 Feb;83(5):14671-714.
2.
Aidara NK, Diop IM, Diallo C, Cherifi H. Detecting Influential Nodes with Centrality Measures via Random Forest in Social Networks. In2024 IEEE Workshop on Complexity in Engineering (COMPENG) 2024 Jul;22: 1-6. IEEE. .
3.
Kim S, Han J. Detecting engagement bots on social influencer marketing. InInternational Conference on Social Informatics 2020 Oct;6:124-136. Cham: Springer International Publishing.
4.
Máiz-Bar C, Abuín-Penas J. The current role of influencers in public relations: Comparing Spain and the USA. Anàlisi. 2022; 67:125-44.
5.
Huang X, Chen D, Wang D, Ren T. Identifying influencers in social networks. Entropy. 2020 Apr 15;22(4):450.

Citation

This is an open access article distributed under the  Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Article metrics

Google scholar: See link

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.