Title: Consumer preference mining method of online marketing platform based on social network analysis

Authors: Xiaodong Chen

Addresses: Department of Economics and Trade, Henan Polytechnic Institute, Nanyang, 473000, China

Abstract: In order to address the problems of low text extraction accuracy, mining accuracy, and effectiveness in existing consumer preference mining methods for online marketing platforms, this article uses social network analysis methods to mine consumer preferences on online marketing platforms. First is the analysis of the node density and individual centrality in consumer social networks. Then, LDA model is selected to extract consumer texts from online marketing platforms, and rough set theory is combined for reduction processing. Finally, through the bidirectional association rule mining method, the consumer preferences of online marketing platforms are mined. The experimental results show that the text extraction accuracy of the proposed method is higher than 93%, and the minimum number of association rules can be reduced to below 2 × 10³ N; the highest confidence level can reach 28.3%, and the highest support level can reach 97.5%, which can effectively explore consumer preferences on online marketing platforms.

Keywords: social network analysis; online marketing platform; consumers; preference mining; rough set; association rules.

DOI: 10.1504/IJNVO.2024.136776

International Journal of Networking and Virtual Organisations, 2024 Vol.30 No.1, pp.82 - 99

Received: 29 Jun 2023
Accepted: 30 Oct 2023
Published online: 21 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article