Title: Data mining analysis method of consumer behaviour characteristics based on social media big data

Authors: Tiantian An

Addresses: Department of Higher Vocational College, Anshan Normal University, An'shan 114000, China

Abstract: In order to solve the problems of low accuracy, high time and small capacity in the current analysis method of consumer behaviour, this paper proposes a method of mining and analysing consumer behaviour feature databased on big data of social media. The big data of social media is preprocessed, and the feature selection model is established to generate the label of social media big data users. k-means algorithm is used to cluster the consumer behaviour feature data, and the multi-dimensional consumption behaviour feature is extracted to construct the hierarchical model of the consumer behaviour feature data. The non-parametric regression method of k-nearest neighbour is used to mining and analysing the characteristics of consumer behaviour. The experimental results show that the accuracy of the proposed method is 92%, the time of feature analysis is only 14 s, and the data analysis capacity is up to 63 T.

Keywords: social media; big data; k-means algorithm; k-nearest neighbour non-parametric regression method; characteristics of consumption behaviour; data mining analysis.

DOI: 10.1504/IJWBC.2022.125492

International Journal of Web Based Communities, 2022 Vol.18 No.3/4, pp.224 - 237

Received: 01 Jun 2021
Accepted: 29 Sep 2021
Published online: 12 Sep 2022 *

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