Understanding Consumers’ Sentiment Expressions in Online Reviews: A Hybrid Approach

La, Liqing; Xu, Feifei; Ren, Qun; Zhu, Feng; Lobsang, Tashi

doi:10.1080/08961530.2021.1982807

Cited by 4 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, as indicated in the results from "after COVID-19" dataset, XGBoost with BoW achieved the highest accuracy of 89.16%. The prediction accuracies achieved in this study can be considered superior to the results of existing studies (Hwang et al, 2020;La et al, 2021). Overall, Logistic regression with TF-IDF and XGBoost with BoW are proposed to have better performances in predicting user satisfaction for healthcare services.…”

Section: Discussionmentioning

confidence: 63%

“…Additionally, Shah et al (2021) confirmed that random forest (accuracy: 93.17%) and logistic regression (accuracy: 90.88%) has a higher accuracy than multinomial and Bernoulli Naïve Bayes models in forecasting user satisfaction with certain products. La et al (2021) predicted tourists' satisfaction by analyzing their online comments with Logistic regression and found the classifier to have an accuracy of 80.95%. Luo et al (2021) analyzed online reviews using random forest to predict positive/negative customer ratings for restaurant services.…”

Section: User Satisfaction With Mobile Healthcare Servicesmentioning

confidence: 99%

See 1 more Smart Citation

Predicting User Satisfaction of Mobile Healthcare Services Using Machine Learning

Lee

Nan

et al. 2022

Journal of Organizational and End User Computing

View full text Add to dashboard Cite

Outbreak of the COVID-19 leads to rapid development of the mobile healthcare services. Given that user satisfaction is of great significance in inducing marketing success in competition markets, this research explores and predicts user satisfaction with mobile healthcare services. Specifically, the current research aimed to design a machine learning model that predicts user satisfaction with healthcare services using big data from Google Play Store reviews and satisfaction ratings. By dealing with the sentimental features in online reviews with five classifiers, the authors find that Logistic regression with term frequency-inverse document frequency (TF-IDF) and XGBoost with Bag of words (BoW) have superior performances in predicting user satisfaction for healthcare services. Based on these results, the authors conclude that such user-generated texts as online reviews can be used to predict user satisfaction, and Logistic regression with TF-IDF and XGBoost with BoW can be prioritized for developing online review analysis platforms for healthcare service providers.

show abstract

Section: Discussionmentioning

confidence: 63%

Section: User Satisfaction With Mobile Healthcare Servicesmentioning

confidence: 99%

Predicting User Satisfaction of Mobile Healthcare Services Using Machine Learning

Lee

Nan

et al. 2022

Journal of Organizational and End User Computing

View full text Add to dashboard Cite

show abstract

“…Still based on the equity theory, when individuals experience strong consumption dissatisfaction, they will desire to vent their negative feelings, leading them to write more enriched reviews. Therefore, we argue that experienced travelers are inclined to post richer reviews with photos, more words and more affective content to express their emotions (Hong et al, 2016;Huang et al, 2017;La et al, 2021). We thus put forward the hypotheses as follows:…”

Section: 22mentioning

confidence: 99%

Influence of travel distance and travel experience on travelers' online reviews: price as a moderator

Deng

Fan

et al. 2022

IMDS

View full text Add to dashboard Cite

PurposeBuilding on a small body of work, the authors' study aims to investigate some important antecedents of online review characteristics in the Chinese restaurant industry.Design/methodology/approachUsing a data set of restaurant reviews collected from a most popular review platform in China, the authors conduct a series of analyses to examine the influence of travel experience and travel distance on travelers' review characteristics in terms of review rating and media richness. The moderating effect of restaurant price on the influence is also investigated.FindingsTravelers with a longer travel distance and more travel experience tend to provide higher and lower online ratings, respectively, which can be explained by the construal level theory (CLT) and the expectation-confirmation theory (ECT), respectively. Furthermore, these strong feelings can then induce travelers to post enriched reviews with more pictures, more words and more affective words to release consumption tension. Besides, restaurant price can moderate these relationships.Originality/valueDistinguished from most studies which mainly focus on the consequences of online review characteristics or antecedents of review helpfulness, the authors pay attention to the effects of travelers' individual differences in terms of travel distance and travel experience on travelers' online reviewing behavior. In addition to review rating, the authors also focus on media richness in terms of visual and textual information. The authors' research findings can benefit restaurant consumers and managers for their online word-of-mouth utilization and management.

show abstract

“…Lee et al [25] indicated that an algorithm combining VADER and machine learning is an effective methodology for sentiment analysis using metaverse mobile application service reviews. La et al [26] found that logistic regression is an appropriate model for analyzing the online comments of tourists. [27] used online restaurant reviews to discover the model that could predict positive or negative scores.…”

Section: Sentiment Analysis Utilizing Social Network Services Datamentioning

confidence: 99%

Robust Sentiment Classification of Metaverse Services Using a Pre-trained Language Model with Soft Voting

2023

KSII TIIS

View full text Add to dashboard Cite

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

show abstract

Understanding Consumers’ Sentiment Expressions in Online Reviews: A Hybrid Approach

Cited by 4 publications

References 50 publications

Predicting User Satisfaction of Mobile Healthcare Services Using Machine Learning

Predicting User Satisfaction of Mobile Healthcare Services Using Machine Learning

Influence of travel distance and travel experience on travelers' online reviews: price as a moderator

Robust Sentiment Classification of Metaverse Services Using a Pre-trained Language Model with Soft Voting

Contact Info

Product

Resources

About