Title: A method for identifying consumer emotional tendency in the 'live streaming+e-commerce' mode

Authors: Jie Liu

Addresses: School of Management, XinXiang University, XinXiang, 453003, China

Abstract: In order to achieve accurate and rapid identification of consumer emotional tendencies, a method for identifying consumer emotional tendencies under the 'live streaming+e-commerce' mode is proposed. Firstly, classify the emotional tendencies of consumers under the 'live streaming+e-commerce' model, mainly into two categories: positive and negative. Secondly, based on the comment data of e-commerce live streaming platforms, construct a benchmark vocabulary of emotional tendencies. Finally, a combination of HowNet similarity and Google similarity is used to identify consumers' emotional tendencies. The experimental results show that compared with existing methods, the accuracy of consumer sentiment orientation recognition in this method is significantly improved, and the recognition time is significantly shortened, and the recognition accuracy remains above 90%.

Keywords: the 'live streaming+e-commerce' model; consumer; emotional orientation identification; HowNet similarity; Google Similarity.

DOI: 10.1504/IJWBC.2024.142484

International Journal of Web Based Communities, 2024 Vol.20 No.3/4, pp.200 - 211

Received: 12 May 2023
Accepted: 10 Oct 2023
Published online: 04 Nov 2024 *

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