Research Article
Trust Forge: Harnessing Machine Learning to Build Trust on Social Networks
@INPROCEEDINGS{10.1007/978-3-031-81171-5_14, author={Kavitha Chitrala and Shanthi Makka and S. Sowjanya}, title={Trust Forge: Harnessing Machine Learning to Build Trust on Social Networks}, proceedings={Broadband Communications, Networks, and Systems. 14th EAI International Conference, BROADNETS 2024, Hyderabad, India, February 16--17, 2024, Proceedings, Part II}, proceedings_a={BROADNETS PART 2}, year={2025}, month={2}, keywords={Naive Bayes online social network trust Direct trust Indirect trust}, doi={10.1007/978-3-031-81171-5_14} }- Kavitha Chitrala
Shanthi Makka
S. Sowjanya
Year: 2025
Trust Forge: Harnessing Machine Learning to Build Trust on Social Networks
BROADNETS PART 2
Springer
DOI: 10.1007/978-3-031-81171-5_14
Abstract
A social media platform is a form of service offered by an online platform that facilitates easy communication between individuals, as well as the establishment of interpersonal connections and social exchanges. Additionally, it supplies users with a webpage where they may create an open persona and engage adding additional users. Trust is a significant concern in social networking sites, and to address this issue, we have employed the Naive Bayes algorithm to establish trust in online networks. This algorithm is implemented through direct and indirect communication, and trust values are calculated using Dempster-Shafer theory and Bayesian conditional. The effectiveness of our proposed approach is demonstrated through the reenactment results obtained with various parameter arrangements. “In summary, our comparison demonstrates that Multi-faceted trust modeling is statistically and significantly superior to Naive Bayes Model in addressing based on accuracy.”
