Research on customer opinion summarization using topic mining and deep neural network

Hong, Minghui; Wang, Heyong

doi:10.1016/j.matcom.2020.12.009

Cited by 19 publications

(9 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the determination of topic number K has an important influence on the analysis results. In information theory, perplexity can be used to measure the quality of samples predicted by a probability model; it is often used to determine the optimal number of topics (Hong & Wang, 2021 ). Based on the degree of confusion and the actual situation, this study identifies the optimal number of topics for CMNC policies, as shown in Eq.…”

Section: Methodsmentioning

confidence: 99%

Quantitative Evaluation of Policies for combining Medical and Nursing Care based on the LDA–PMC Model: A Comparative Analysis of Typical Chinese Provinces

2022

Public Organiz Rev

View full text Add to dashboard Cite

Improving and optimizing the policy system of combined medical and nursing care (CMNC) is an important driving force in the development of China’s pension industry. Using a latent Dirichlet allocation–policy modeling consistency model, this study analyzes 25 key policies related to CMNC to develop a policy evaluation index system and evaluates the CMNC policies of four provinces in China: Shandong, Sichuan, Jiangsu, and Hubei. It highlights issues facing China’s CMNC policy, including the poor use of policy tools, insufficient publicity, lack of insurance protection for employees, and lack of local policies’ pertinence. Finally, a policy optimization path is proposed.

show abstract

Section: Methodsmentioning

confidence: 99%

Quantitative Evaluation of Policies for combining Medical and Nursing Care based on the LDA–PMC Model: A Comparative Analysis of Typical Chinese Provinces

2022

Public Organiz Rev

View full text Add to dashboard Cite

show abstract

“…Although this framework is favorable for identifying causes of complaints, it is slightly too crude. Because these product reviews are too abundant, lengthy and descriptive, Hong and Wang (2021) proposed a deep neural network based framework to summarize customer opinions, including both positive and negative comments, from product reviews. The summaries provide users the valuable opinions on product attributes.…”

Section: Customer Complaint Analysismentioning

confidence: 99%

Using an Ontology-Based Neural Network and DEA to Discover Deficiencies of Hotel Services

Chiang

Huang³

et al. 2022

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

Companies can gain critical real-time insights into customer requirements and service evaluation by mining social media. To acquire the service performance and improve the service deficiencies for hotels, this research proposes a benchmark-based performance evaluation model for hotel service to enable hotel managers to assess the service performance. In the case of non-benchmark service hotels, the identification and improvement model for non-benchmark criteria can recognize and analyze the required quantities of performance improvements for non-benchmark criteria. For understanding the causes of service deficiencies, this research mines the online posts and creates a hierarchical ontology of service deficiencies for hotels. A hierarchical ontology-based neural network is proposed to automatically identify the causes of service deficiencies. This study employs an online forum as a case to achieve the identification accuracy of causes of service deficiencies of 92.68%. The analytical result can demonstrate the significant effectiveness and practical value of the proposed methodology.

show abstract

“…More researchers have recently addressed the analysis of customer comments for efficient complaint handling in this respect. For example, Hong and Wang (2021) proposed a framework to summarize customer opinions, including both positive and negative comments, from product reviews using neural networks. The effectiveness of the framework was tested with six datasets from real-world business scenarios.…”

Section: Related Workmentioning

confidence: 99%

Categorization of Customer Complaints in Food Industry Using Machine Learning Approaches

Bozyiğit¹,

Doğan²,

Kılınç³

2022

Journal of Intelligent Systems: Theory and Applications

View full text Add to dashboard Cite

Customer feedback is one of the most critical parameters that determine the market dynamics of product development. In this direction, analyzing product-related complaints helps sellers to identify the quality characteristics and consumer focus. There have been many studies conducted on the design of Machine Learning (ML) systems to address the causes of customer dissatisfaction. However, most of the research has been particularly performed on English. This paper contributes to developing an accurate categorization of customer complaints about package food products, written in Turkish. Accordingly, various ML algorithms using TF-IDF and word2vec feature representation strategies were performed to determine the category of complaints. Corresponding results of Linear Regression (LR), Naive Bayes (NB), k Nearest Neighbour (kNN), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) classifiers were provided in related sections. Experimental results show that the best-performing method is XGBoost with TF-IDF weighting scheme and it achieves %86 F-measure score. The other considerable point is word2vec based ML classifiers show poor performance in terms of F-measure compared to the TF-IDF term weighting scheme. It is also observed that each experimented TF-IDF based ML algorithm gives a more successful prediction performance on the optimal subsets of features selected by the Chi Square (CH2) method. Performing CH2 on TF-IDF features increases the F-measure score from 86% to 88% in XGBoost.

show abstract

Research on customer opinion summarization using topic mining and deep neural network

Cited by 19 publications

References 76 publications

Quantitative Evaluation of Policies for combining Medical and Nursing Care based on the LDA–PMC Model: A Comparative Analysis of Typical Chinese Provinces

Quantitative Evaluation of Policies for combining Medical and Nursing Care based on the LDA–PMC Model: A Comparative Analysis of Typical Chinese Provinces

Using an Ontology-Based Neural Network and DEA to Discover Deficiencies of Hotel Services

Categorization of Customer Complaints in Food Industry Using Machine Learning Approaches

Contact Info

Product

Resources

About