Topic modelling and opinion mining of user generated content on the internet using machine learning: An analysis of postpartum care centres in Shanghai

Issue title: Artificial Intelligence and Advanced Manufacturing (AIAM 2020)

Guest editors: Shengzong Zhou

Article type: Research Article

Authors: Jia, Susan (Sixue)^a | Wu, Banggang^{b; *}

Affiliations: [a] School of Finance and Business, Shanghai Normal University, Shanghai, China | [b] Business School, Sichuan University, Chengdu, Sichuan, China

Correspondence: [*] Corresponding author. Banggang Wu, Business School, Sichuan University, Chengdu, Sichuan, China. E-mail: wubg@scu.edu.cn.

Abstract: In order to reach a compromise between adhering to the traditional culture and embracing the modern lifestyle, more and more Asian moms are heading towards postpartum care centres for postpartum recovery. However, research regarding the quality of care of these postpartum care centres is nearly missing from the literature. This paper investigated the status quo of the postpartum care centres in Shanghai, China from mothers’ perspectives by means of analysing the 34280 pairs of ratings and reviews posted by postpartum care centre customers on the internet with machine learning and text mining. Results show that the mothers are generally satisfied with the studied care centres. Meanwhile, the 13 major topics in the customer online reviews were identified, which provide an overview of the interaction between a mother and a care centre. In addition, weight of topic analysis suggests that the studied care centres can further improve in the areas of support team, environment, and facility.

Keywords: User-generated content, text mining, postpartum care, latent Dirichlet allocation

DOI: 10.3233/JIFS-189726

Journal: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 3, pp. 4661-4668, 2021