Open Access

ARTICLE

A Query-Based Greedy Approach for Authentic Influencer Discovery in SIoT

Farah Batool¹, Abdul Rehman², Dongsun Kim^2,*, Assad Abbas¹, Raheel Nawaz³, Tahir Mustafa Madni¹

1 COMSATS University Islamabad, Islamabad, Pakistan
2 School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, Korea
3 Department of Operations, Technology, Events and Hospitality Management, Manchester Metropolitan University, United Kingdom

* Corresponding Author: Dongsun Kim. Email:

Computers, Materials & Continua 2023, 74(3), 6535-6553. https://doi.org/10.32604/cmc.2023.033832

Received 29 June 2022; Accepted 13 October 2022; Issue published 28 December 2022

Abstract

The authors propose an informed search greedy approach that efficiently identifies the influencer nodes in the social Internet of Things with the ability to provide legitimate information. Primarily, the proposed approach minimizes the network size and eliminates undesirable connections. For that, the proposed approach ranks each of the nodes and prioritizes them to identify an authentic influencer. Therefore, the proposed approach discards the nodes having a rank (α) lesser than 0.5 to reduce the network complexity. α is the variable value represents the rank of each node that varies between 0 to 1. Node with the higher value of α gets the higher priority and vice versa. The threshold value α = 0.5 defined by the authors with respect to their network pruning requirements that can be vary with respect to other research problems. Finally, the algorithm in the proposed approach traverses the trimmed network to identify the authentic node to obtain the desired information. The performance of the proposed method is evaluated in terms of time complexity and accuracy by executing the algorithm on both the original and pruned networks. Experimental results show that the approach identifies authentic influencers on a resultant network in significantly less time than in the original network. Moreover, the accuracy of the proposed approach in identifying the influencer node is significantly higher than that of the original network. Furthermore, the comparison of the proposed approach with the existing approaches demonstrates its efficiency in terms of time consumption and network traversal through the minimum number of hops.

---

Keywords

---