A User-Generated Content-Based Multi-Criteria Decision-Making Approach with Large-Scale Group Clustering and Interaction

40 Pages Posted: 8 Nov 2023

See all articles by Yuanyuan Liang

Yuanyuan Liang

Beijing Institute of Technology

Yanbing Ju

Beijing Institute of Technology

Xiao-Jun Zeng

The University of Manchester

Hao Li

The University of Manchester

Peiwu Dong

Beijing Institute of Technology

Tian Ju

China Agricultural University

Abstract

Due to the popularity of social media and the influence of netizens’ behaviors as well as social activities, there are increasingly interests about merging traditional large-scale group decision making (LSGDM) with social network based on the user-generated content (UGC). This study develops a UGC-based multi-criteria decision-making approach that manages incomplete evaluation information and explores the interactions between clustered groups under social network. Firstly, by utilizing topic modelling techniques, various criteria with respect to specific product or service are retrieved from online reviews and criterion weights are also derived. Secondly, a novel clustering method based on node potential influence and the m-ary adjacency relation is designed to categorize large-scale decision makers into small and manageable clusters. Thirdly, considering that the loss of evaluation information occurs during decision making process, Cornish-Fisher expansion is utilized to deduce the mean, standard variance, and kurtosis estimators of the incomplete information, which can be further converted into cloud models by our proposed backward cloud transformation algorithm. Finally, a minimizing bi-capacity entropy optimization model is constructed to derive 2-additive bi-capacity parameters and their corresponding bipolar Möbius transforms that are adopted to depict the interactions between clusters. A bipolar Choquet integral information aggregation approach is also presented to aggregate opinions in the form of cloud models of different clusters to rank alternatives. A case study on General Practitioners medical service in United Kingdom and a comparative analysis are further performed to validate our proposal.

Keywords: User-generated Content, Large-scale group decision-making, Clustering, Cloud model, Bi-capacity identification

Suggested Citation

Liang, Yuanyuan and Ju, Yanbing and Zeng, Xiao-Jun and Li, Hao and Dong, Peiwu and Ju, Tian, A User-Generated Content-Based Multi-Criteria Decision-Making Approach with Large-Scale Group Clustering and Interaction. Available at SSRN: https://ssrn.com/abstract=4626674 or http://dx.doi.org/10.2139/ssrn.4626674

Yuanyuan Liang

Beijing Institute of Technology ( email )

5 South Zhongguancun street
Center for Energy and Environmental Policy Researc
Beijing, 100081
China

Yanbing Ju (Contact Author)

Beijing Institute of Technology ( email )

5 South Zhongguancun street
Center for Energy and Environmental Policy Researc
Beijing, 100081
China

Xiao-Jun Zeng

The University of Manchester ( email )

Oxford Road
Manchester, N/A M13 9PL
United Kingdom

Hao Li

The University of Manchester ( email )

Oxford Road
Manchester, M13 9PL
United Kingdom

Peiwu Dong

Beijing Institute of Technology ( email )

5 South Zhongguancun street
Center for Energy and Environmental Policy Researc
Beijing, 100081
China

Tian Ju

China Agricultural University ( email )

Beijing
China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
29
Abstract Views
81
PlumX Metrics