E-word of mouth sentiment analysis for user behavior studies
Introduction
As global Internet presentations continue to increase, the number of consumers who provide online comments have increased significantly (Lu & Bai, 2021). If exploited properly, abundant data should produce useful insights. One insight that can be obtained from the statistics is the information of electronic word of mouth (EWOM). EWOM is known for its significant impact on consumer behavior (Tobon & García-Madariaga, 2021). EWOM communication framework demostrates the direct relation of adopting EWOM and consumers’ willingness to purchase. EWOM can provide objective information for more and more consumers who trust these communications (Yaniv & Shalom, 2021).Comment mining concerning sentiment analysis is considered to be a suite of proceedings for identifying sentiments, opinions and author's attitudes in texts, transforming them into meaningful information and using them to make business decisions (Siddiqui et al., 2021).
Sentiment classification identifies opinions and arguments in a given text, and it is part of opinion mining. It tries to find statements of agreement or disagreement in comments or reviews that involve positive, negative or neutral statements. Sentiment analysis has attracted widespread attention and has been widely used in many fields (Wang & Zhang, 2020). Up to now, many approaches of sentiment analysis have been proposed, which can be roughly split into document-level, sentence-level and aspect-level(Jiang, Chan, Eichelberger, Ma, & Pikkemaat, 2021).Most of the work of sentiment analysis can be achieved by assessing the document's polarity.Phrase and sentence levels have become common increasingly in recent years.Dictionary-based and machine learning approaches are two of the most common uses of emotion analysis(Ahlem & Khalil, 2020). Building emotional dictionary is the main way to realize sentiment analysis. For example,SentiWordNet (Madani, Erritali, Bengourram, & Sailhan, 2020), SenticNet (Hung, Wu, & Chou, 2020), and OpinionFinder (Wiebe et al., 2005) are famous emotional dictionaries. Sentiment lexicon plays a vital role, because it includes the emotional polarity of a word or phrase which can be used to classify sentiment of textual data.
Most of the available studies is based on sentiment analysis of product reviews. However in this thesis, we focus on discussing the domain of online dating service's (ODS) reviews,because this domain is different from the other product reviews (Wang, 2020). When a person writes down her/his feelings about the usage of the ODS, she/he probably comments not only on website elements (e.g., easy to use, perfect function) but also on the people who have used the website (e.g., dater, matchmaker, friend, parents). Therefore, the review features of the ODS are more complex than the products' reviews, and it's more challenging to analyze the ODS’s reviews. This paper describes a method used natural language processing(NLP) and emotion lexicon generation (Chang, Hwang, & Wu, 2021) to classify the ODS’s reviews (이득영, 장선우, & 전한종, 2019).
Many opinion mining studies have been conducted to analyze unstructured text data including customer reviews, blogs, tweets, news and online (Al-Mashhadany, Hamood, Al-Obaidi, & Al-Mashhsdany, 2021).However, there are still some problems to be solved. First, there is less research on emotion analysis based on the theory of user's behaviour analysis. Different from traditional sentiment analysis which is based on the products in the customer reviews, the sentiment analysis method based on user behavior analysis is to extract the user's concept and analyze the emotion from the user's point of view.Next, there were few sentiment analysis studies based on multiple category problem. Traditional sentiment analysis is generally based on document-level (Li, H, Kang, Yang, & Zong, 2019), sentence-level (Eng, Nawab, & Shahiduzzaman, 2021) and aspect-level (Lu, Zhu, Zhang, Wu, & Guo, 2020),but this paper is based on the concept-level and multi-sentiment classification problem. The main problem is the extraction of concepts and the classification of multiple emotions (Sznycer & Lukaszewski, 2019).
Our work tries to perform sentiment analysis on users' behaviors influenced by conflict environmental factors obtained by using machine learning models.We selected 4800 controversial context of online dating service (ODS) which had extremely negative/positive rates of popularity in a online dating sites, extracted linguistic features from them using NLP,and compared their performances within accuracy using machine learning models: Naive Bayes (NB), K-Nearest-Neighbor (KNN) and Support Vector Machines (SVM). To sum up, our contributions in this study are as follows:(1) A new method of learning training data in the form of classifier labels is proposed. By combining machine learning with dictionary methods, the automatically generated questionnaire has more value and credibility.(2) The opinion mining of comments and the analysis of sentiment classification are based on user behavior, rather than the analysis method based on product features in traditional research. It provides a new direction for sentiment analysis in the future by exploring opinions and classifying emotions from a new perspective.(3) The automatic lexico-based classifier is used to classify user behaviors according to eight features of social cognitive theory as influencing factors. Four classifiers were constructed according to the eight features, and a new constructed dictionary was used to correct the false prediction results of the four classifiers, and vocabulary and learning methods were fused to make up for the defects of the two.
This is followed by a discussion of 4 areas: Section 2 describes the work related to EWOM, opinion mining and emotion analysis. Section 3 develops the narrative of our approach. Section 4 report on the case study of SOD. In section 5, experiment results of efficiency,coverage and discussion are provided. Conclusions and further tasks are presented in section 6.
Section snippets
Electronic word of mouth
Electronic word-of-mouth (EWOM) is defined as an online sharing campaign that includes a wealth of consumer information from experienced consumers' opinions and recommendations on vendors/products (Donthu, Kumar, Pandey, Pandey, & Mishra, 2021). EWOM is becoming an essential part of the online experience both for marketers and customers. EWOM can greatly attract people's attention and raise the topic of discussion. In addition, EWOM is widely used by online visitors as a reference (Wu, Song,
Proposed method
Most previous studies on opinion mining and sentiment classification have been analyzed from the perspective of product attributes. The usual method is to determine the product attributes through the statistics of the word frequency, and judge the emotional tendency of the sentence. We proposed a novel method for learning a classifier from labeled training data,which can then be used to classify eight features from the aspect of user’s behavior. Our proposed method has novelties on both main
Data collection and pre-processing
(1) Data collection. We gathered data from a famous public word-of-mouth website in China, Baidu reputation.com. We selected this website for several reasons. First, it is one of the most popular consumer word-of-mouth platforms in China and founded in 2014 by Baidu.com which is the leading Chinese search engine. In addition, it is a famous UGC (User Generated Content) aggregate interactive platform. We selected the six famous companies in Chinese ODS industry, including Baihe, Youyuan, Zhenai,
Performance metrics and estimation method
Various metrics such as precision, recall and accuracy are important factors in measuring the performance of evaluation algorithms and sentiment analysis, and F1 score (Ahmad, Asghar, Alotaibi, & Khan, 2020). These metrics are founded on the following concepts, which relate to the correct or incorrect classification of events (Esuli and Sebastiani, 2010).
- •
True Positive (TP): the occurrence has been correctly classified as part of the category;
- •
False positive (FP): the occurrence has been
Conclusion and future work
Sentiment classification in social communication media, particularly online chat services, has attracted considerable research attention.However, existing research largely focus on the product's review. In this paper we focus on the reviews of online dating service (ODS) because this is different from the product's reviews. We tried to conduct sentiment analysis of user’ behavior influenced by conflict environmental factors using machine tools to understand availability through comparing of the
CRediT authorship contribution statement
Hui Li: Validation. Qi Chen: . Zhaoman Zhong: Data curation, Funding acquisition, Formal analysis. Rongrong Gong: . Guokai Han: .
Acknowledgments
The research is supported byNational Natural Science Foundation of China (No.72174079, No. 1210050123, No. 72101045), Cooperation and Education Project of Ministry Education(201701028110, 201701028011, 201902159041), Natural Science Foundation of the Jiangsu Higher Education Institutions of China( No. 19KJB520004), Jiangsu Province “333” project (BRA2020261), Lianyungang “521 project”, Science and Technology project of Lianyungang High-tech Zone( No. ZD201912), Teaching reform research project
Hui Li, female, born in October 1979 in Lianyungang, Jiangsu Province, P.R. China. She received her BE degree in computer science and technology from the Yang Zhou University in 2007. She received her Doctoral degree in the School of Information & Electrical Engineering in China University of Mining & Technology in 2016. Her current research interest includes data mining, information processing, social network. She has published more than 20 papers in various journals.
References (57)
- et al.
Social Cognitive Theory of Posttraumatic Recovery: The Role of Perceived Self-Efficacy
Behaviour research and therapy
(2004) - et al.
Learning bilingual sentiment lexicon for online reviews
Electronic Commerce Research and Applications
(2021) - et al.
Co-training semi-supervised deep learning for sentiment classification of mooc forum posts
Symmetry
(2019) - et al.
Mapping the electronic word-of-mouth (eWOM) research: A systematic review and bibliometric analysis
Journal of Business Research
(2021) - et al.
Identifying competitors through comparative relation mining of online reviews in the restaurant industry
International Journal of Hospitality Management
(2018) - et al.
Social sharing of consumption emotion in electronic word of mouth (ewom): a cross-media perspective
Journal of Business Research
(2021) - et al.
Inferring sentiments from supervised classification of text and speech cues using fuzzy rules
Procedia Computer Science
(2020) Stacked generalization
Neural Netw
(1992)- et al.
An opinion spread prediction model with twitter emotion analysis during algeria’s hirak
The Computer Journal
(2020) - et al.
Classification of poetry text into the emotional states using deep learning technique
IEEE Access
(2020)
Extracting numerical data from unstructured arabic texts (enat)
Indonesian Journal of Electrical Engineering and Computer Science
Goodness-of-fit test for a logistic regression model fitted using survey sample data
The Stata Journal
Social Foundation of Thought and Action: A Social-Cognitive View
Englewood Cliffs)
Human Agency in Social Cognitive Theory
American psychologist
A review on lexicon-based and machine learning political sentiment analysis using tweets
International Journal of Semantic Computing
Context-sensitive learning methods for text categorization
ACM Transactions on Information Systems (TOIS)
Support-vector networks
Mach Learn
What Does the Brain Tell Us About Trust and Distrust? Evidence from a Functional Neuroimaging Study
Mis Quarterly
Improving accuracy of the sentence-level lexicon-based sentiment analysis using machine learning
International Journal of Scientific Research in Computer Science Engineering and Information Technology
Machines that learn how to code open-ended survey data
International Journal of Market Research
Predicting the semantic orientation of adjectives
The Emoji Sentiment Lexicon: Analysing Consumer Emotions in Social Media Communication
49th European Marketing Academy (EMAC) Annual Conference
Measuring and managing consumer sentiment in an online community environment
Journal of Marketing Research
SenticNet
Sentic Computing
Sentiment analysis of online destination image of Hong Kong held by mainland Chinese tourists
Current Issues in Tourism
Text classification using novel term weighting scheme-based improved tf-idf for internet media reports
Mathematical Problems in Engineering
Operational criteria for designing information retrieval systems
American Documentation
The effects of eWOM volume and valence on product sales–an empirical examination of the movie industry
International Journal of Advertising
Cited by (57)
Graph embedding approaches for social media sentiment analysis with model explanation
2024, International Journal of Information Management Data InsightsMultimodal sentiment analysis: A survey
2023, DisplaysUnderstanding AI tool engagement: A study of ChatGPT usage and word-of-mouth among university students and office workers
2023, Telematics and InformaticsIs ChatGPT competent? Heterogeneity in the cognitive schemas of financial auditors and robots
2023, International Review of Economics and FinanceCausal aware parameterized quantum stochastic gradient descent for analyzing marketing advertisements and sales forecasting
2023, Information Processing and ManagementBreaking down linguistic complexities: A structured approach to aspect-based sentiment analysis
2023, Journal of King Saud University - Computer and Information Sciences
Hui Li, female, born in October 1979 in Lianyungang, Jiangsu Province, P.R. China. She received her BE degree in computer science and technology from the Yang Zhou University in 2007. She received her Doctoral degree in the School of Information & Electrical Engineering in China University of Mining & Technology in 2016. Her current research interest includes data mining, information processing, social network. She has published more than 20 papers in various journals.
Qi Chen is an assistant professor in the Department of Management Science and Engineering in the School of Business and Management at Dalian University of Technology (DUT), China. She received her Ph.D., M.S. and B.S. in Management Science and Engineering from Harbin Institute of Technology (HIT) in China. Her research interests are in the areas of security, privacy and trust, management information systems, social media. She has published articles in journals and conferences such as International
Zhao-Man Zhong, male, born in 1977, received his PhD degree in computer science from Shanghai University in 2011. He is currently an associated professor of Jiangsu Ocean University. His research interests are information retrieval and artificial intelligence.
Rongrong Gong, is a graduate student at Jiangsu Ocean University. Her main research direction is intelligent recommendation and artificial intelligence.
Guokai Han, is a junior student at Jiangsu Ocean University, majoring in software engineering. He has won the National Computer Design Competition.
- 1
Hui Li and QI Chen are co-first authors of this article