Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model

A BERT-MDLP-Bayesian Network model (BMB) is proposed to analyze the improvement strategy of e-commerce products based on user generated content (UGC). The proposed model can be represented into four parts: clearing redundant data on the obtained UGC, extracting product attributes and word vector to...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming-Fang Li, Guo-Xiang Zhang, Lu-Tao Zhao, Tao Song
Format: Article
Language:English
Published: Springer 2022-06-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1319157822001021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849324829827661824
author Ming-Fang Li
Guo-Xiang Zhang
Lu-Tao Zhao
Tao Song
author_facet Ming-Fang Li
Guo-Xiang Zhang
Lu-Tao Zhao
Tao Song
author_sort Ming-Fang Li
collection DOAJ
description A BERT-MDLP-Bayesian Network model (BMB) is proposed to analyze the improvement strategy of e-commerce products based on user generated content (UGC). The proposed model can be represented into four parts: clearing redundant data on the obtained UGC, extracting product attributes and word vector to generate product attributes, establishing product attribute Bayesian network corresponding to UGC, and inferring the causal relationship between product attributes. In order to verify the effectiveness of the proposed model, an amazon tablet product is used for empirical analysis. Compared with the traditional model, BMB model has better performance in product feature mining in three aspects of feature diversity, feature long tail and attribute difference. In application, the model can effectively describe the core problems of products, and provide suggestions for e-commerce to modify marketing strategies and determine the new direction of product development.
format Article
id doaj-art-fd0b7e841bb34aabaa7b7fe28ac632b1
institution Kabale University
issn 1319-1578
language English
publishDate 2022-06-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-fd0b7e841bb34aabaa7b7fe28ac632b12025-08-20T03:48:35ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782022-06-013462720273210.1016/j.jksuci.2022.03.018Extracting product competitiveness through user-generated content: A hybrid probabilistic inference modelMing-Fang Li0Guo-Xiang Zhang1Lu-Tao Zhao2Tao Song3School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing, ChinaSchool of Mathematics and Physics, University of Science and Technology Beijing, Beijing, China; Center for Energy and Environmental Policy Research, Beijing Institute of Technology, Beijing, China; School of Management and Economics, Beijing Institute of Technology, Beijing, China; Corresponding author at: School of Management and Economics, Beijing Institute of Technology, Beijing, China.School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, China; Cheil PengTai Company Limited, Beijing, ChinaA BERT-MDLP-Bayesian Network model (BMB) is proposed to analyze the improvement strategy of e-commerce products based on user generated content (UGC). The proposed model can be represented into four parts: clearing redundant data on the obtained UGC, extracting product attributes and word vector to generate product attributes, establishing product attribute Bayesian network corresponding to UGC, and inferring the causal relationship between product attributes. In order to verify the effectiveness of the proposed model, an amazon tablet product is used for empirical analysis. Compared with the traditional model, BMB model has better performance in product feature mining in three aspects of feature diversity, feature long tail and attribute difference. In application, the model can effectively describe the core problems of products, and provide suggestions for e-commerce to modify marketing strategies and determine the new direction of product development.http://www.sciencedirect.com/science/article/pii/S1319157822001021Text miningBayesian networkSocial mediaSentiment analysisUser-generated content
spellingShingle Ming-Fang Li
Guo-Xiang Zhang
Lu-Tao Zhao
Tao Song
Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model
Journal of King Saud University: Computer and Information Sciences
Text mining
Bayesian network
Social media
Sentiment analysis
User-generated content
title Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model
title_full Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model
title_fullStr Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model
title_full_unstemmed Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model
title_short Extracting product competitiveness through user-generated content: A hybrid probabilistic inference model
title_sort extracting product competitiveness through user generated content a hybrid probabilistic inference model
topic Text mining
Bayesian network
Social media
Sentiment analysis
User-generated content
url http://www.sciencedirect.com/science/article/pii/S1319157822001021
work_keys_str_mv AT mingfangli extractingproductcompetitivenessthroughusergeneratedcontentahybridprobabilisticinferencemodel
AT guoxiangzhang extractingproductcompetitivenessthroughusergeneratedcontentahybridprobabilisticinferencemodel
AT lutaozhao extractingproductcompetitivenessthroughusergeneratedcontentahybridprobabilisticinferencemodel
AT taosong extractingproductcompetitivenessthroughusergeneratedcontentahybridprobabilisticinferencemodel