Opinion Mining Studies Research Articles

Does the Tourist Appreciate Your Employees? Prioritizing Service Employee Improvements Based on User-Generated Content Mining

While a multitude of opinion mining studies have examined the impact of attribute performance on customer satisfaction, they have offered limited insights into the role performance of service employees by investigating tourists’ experiences. Focusing on the hotel industry, this study investigated tourists’ evaluations of service personnel by scrutinizing 68,439 hotel reviews and explored the asymmetric effects of employee performance on customer satisfaction according to service employee functions and traveler types. The results indicate that different travelers have distinct expectations of different kinds of services, thereby moderating the asymmetric impact of role performance on tourist satisfaction. Manager employee, in particular, constitutes an excitement factor for family, solo, and couple travelers. The findings have implications for the formulation of operation strategies to promote tourists’ satisfaction rather than frustration. This study contributes to the literature by offering a novel understanding of the asymmetric effect of customer–personnel interactions on tourist satisfaction.

TEXT ANALYTICS OF OPINION-POLL ON ADOPTION OF DIGITAL COLLABORATIVE TOOLS FOR ACADEMIC PLANNING USING VADER-BASED LEXICON SENTIMENT ANALYSIS

The fast growing community of digital collaborative users across the globe continued to witness breaking of new frontiers in hitherto industries where deployment of traditional methods of computing had continued to hold sway. Notwithstanding the widespread deployment computing tools in educational institutions in Nigeria, the use of online collaborative tools is limited and seldom a commonplace in tertiary educational institutions for academic planning. This study therefore aims at extracting emotions from opinions expressed by stakeholders in the academic research industry regarding the utilitarian possibilities of collaborative tools for academic planning purposes through text mining. A VADER-based approach to Sentiment Analysis is modeled in the opinion mining study of the natural language processing use case. Assigning negative, positive, neutral and compound values to the uni-gram and bi-gram tokenized dictionary-of-known-words, experimental result shows a -0.10 mean sentiment negative score constituting a 17.27% clusters of respondents not favorably disposed to the idea while a 22.7% cluster of highly convinced respondents expressed positive sentiments about the use of collaborative tools with a mean sentiment score of 0.49. A 60.01% cluster of average respondents who expressed neutral sentiments actually tilts towards a positive emotion with a 0.39 mean score.

Proposal of an Automated Tool for the Application of Sentiment Analysis Techniques in the Context of Marketing

Currently, the opinions and comments made by customers on e-commerce portals regarding different products and services have great potential for identifying customer perceptions and preferences. Based on the above, there is a growing need for companies to have automated tools based on sentiment analysis through polarity analysis, which allow the examination of customer opinions to obtain quantitative indicators from qualitative information that enable decision-making in the context of marketing. In this article, we propose the construction of an automated tool for conducting opinion mining studies, which can be used in a transparent way to the algorithmic process by the marketing units of companies for decision making. The functionality of the proposed tool was verified through a case study, in which the opinions obtained from electronic commerce website concerning one of the best-selling technological products were investigated.

Implicit Feedback Recommendation Method Based on User-Generated Content

Studying recommendation method has long been a fundamental area in personalized marketing science. The rating data sparsity problem is the biggest challenge of recommendations. In addition, existing recommendation methods can only identify user preferences rather than customer needs. To solve these two bottleneck problems, we propose a novel implicit feedback recommendation method using user-generated content (UGC). We identify product feature and customer needs from UGC using Convolutional Neural Network (CNN) model and textual semantic analysis techniques, measure user-product fit degree introducing attention mechanism and antonym mechanism, and predict user rating based on user-product fit degree and user history rating data. Using data from a large-scale review sites, we demonstrate the effectiveness of our proposed method. Our study makes several research contributions. First, we propose a novel recommendation method with strong robustness against sparse rating data. Second, we propose a novel recommendation method based on the customer need-product feature fit. Third, we propose a novel approach to measure the fit degree of customer needs-product feature, which can effectively improve the performance of recommendation method. Our study also indicates the following findings: (1) UGC can be used to predict user ratings with no user rating records. This finding has important implications to solve the sparsity problem of recommendations thoroughly. (2) The customer need-based recommendation method has better performance than existing user preference-based recommendation methods. This finding sheds light on the necessity of mining customer need for recommendation methods. (3) UGC can be used to mine customer need and product features. This finding indicates that UGC also can be used in the other studies requiring information about customer need and product feature. (4) Comparing the opinions of user review should not be solely on the basis of semantic similarity. This finding sheds light on the limitation of existing opinion mining studies.

La minería de opinión para el análisis del discurso de odio en las redes sociales / Opinion mining for the analysis of hate speech in social networks. Un estudio de caso sobre Paulo Freire en YouTube durante el periodo 2007-2019 / A case study on Paulo Freire on YouTube during the period 2007-2019

This work investigates some of the possibilities of opinion mining studies, or sentiment analysis, in audiovisual materials present on the Internet. From the comments made on YouTube to an interview with Paulo Freire, we have been able to extract trends and guidelines from a historical series of comments between the period 2007-2019. Thanks to the use of some R packages and the analysis of the metrics provided by YouTube, it has been possible to verify that the comments were following a trend that clearly coincided with key political moments in Brazil. The comments were influenced by opinion groups that sought to destabilize and despise any element contrary to their ideas.

A Opinion-Mining Study on Public Consciousness and Social Effects of Creative Education

A Opinion-Mining Study on Public Consciousness and Social Effects of Creative Education

A systematic literature review: Opinion mining studies from mobile app store user reviews

The mobile app ecosystem and user reviews contain a wealth of information about user experience and expectations.Developers and app store regulators could leverage the information to better understand their audience.The automated extraction of app features in online reviews does not consider the nature of the review text.Opinion spam or fake review detection is one of the largest problems in the domain. As mobile devices have overtaken fixed Internet access, mobile applications and distribution platforms have gained in importance. App stores enable users to search for, purchase and install mobile applications and then give feedback in the form of reviews and ratings. A review might contain information about the users experience with the app and opinion of it, feature requests and bug reports. Hence, reviews are valuable not only to users who would like to find out what others think about an app, but also to developers and software companies interested in customer feedback.The rapid increase in the number of applications and total app store revenue has accelerated app store data mining and opinion aggregation studies. While development companies and app store regulators have pursued upfront opinion mining studies for business intelligence and marketing purposes, research interest into app ecosystem and user reviews is relatively new. In addition to studies examining online product reviews, there are now some academic studies focused on mobile app stores and user reviews.The objectives of this systematic literature review are to identify proposed solutions for mining online opinions in app store user reviews, challenges and unsolved problems in the domain, any new contributions to software requirements evolution and future research direction.

Opinion Mining and Information Fusion: A survey

Interest in Opinion Mining has been growing steadily in the last years, mainly because of its great number of applications and the scientific challenge it poses. Accordingly, the resources and techniques to help tackle the problem are many, and most of the latest work fuses them at some stage of the process. However, this combination is usually executed without following any defined guidelines and overlooking the possibility of replicating and improving it, hence the need for a deeper understanding of the fusion process becomes apparent. Information Fusion is the field charged with researching efficient methods for transforming information from different sources into a single coherent representation, and therefore can be used to guide fusion processes in Opinion Mining. In this paper we present a survey on Information Fusion applied to Opinion Mining. We first define Opinion Mining and describe its most fundamental aspects, later explain Information Fusion and finally review several Opinion Mining studies that rely at some point on the fusion of information.

A Preliminary Investigation of User Perception and Behavioral Intention for Different Review Types: Customers and Designers Perspective

Existing opinion mining studies have focused on and explored only two types of reviews, that is, regular and comparative. There is a visible gap in determining the useful review types from customers and designers perspective. Based on Technology Acceptance Model (TAM) and statistical measures we examine users' perception about different review types and its effects in terms of behavioral intention towards using online review system. By using sample of users (N = 400) and designers (N = 106), current research work studies three review types, A (regular), B (comparative), and C (suggestive), which are related to perceived usefulness, perceived ease of use, and behavioral intention. The study reveals that positive perception of the use of suggestive reviews improves users' decision making in business intelligence. The results also depict that type C (suggestive reviews) could be considered a new useful review type in addition to other types, A and B.