• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.19 no.5
• /
• pp.1-11
• /
• 2024

Online reviews play a crucial role in assessing a company's market value and are a significant factor influencing profitability. As such, sentiment analysis of online reviews has emerged as a key indicator for predicting business success. This study focuses on restaurant reviews from Yelp, one of the leading online review platforms, utilizing the Yelp Open Dataset. Six machine learning algorithms were applied to predict the sentiment polarity of these reviews: Logistic Regression, Support Vector Machine (SVM), Random Forest, Gradient Boosting Machine (GBM), XGBoost, and LightGBM. Performance evaluations demonstrated that Logistic Regression, SVM, and LightGBM achieved the highest accuracy, with a score of 0.91. The primary contribution of this study is its ability to transform unstructured review text into quantifiable data, enabling businesses, especially startups, to effectively analyze customer feedback and predict ratings. These insights are expected to assist business owners in forecasting consumer behavior and developing strategic marketing approaches.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.49-62
• /
• 2022

Online customer review data can be easily collected on the Internet and also they describe sentimental evaluation of a product in different aspects. Previous sentiment analysis studies evaluate the degree of sentiment with review data, which may have multiple sentences describing different product aspects. Since different aspects of a product can be described in a sentence, the proposed method suggested analyzing a sentence to build a pair of a product aspect terms and sentimental terms. Bidirectional LSTM and CRF algorithms were used in this paper. A pair of aspect terms and sentimental terms are evaluated by pre-defined evaluation rules. The paper suggested using the result of evaulation as inputs of QFD, so that the quantified customer voices effect on the requirements of a new product. Online reviews for a hair dryer were used as an example showing that the proposed approach can derive reasonable sentiment analysis results.

• Journal of Distribution Science
• /
• v.22 no.4
• /
• pp.11-22
• /
• 2024

Purpose: This research delves into the various factors that influence the performance of restaurant businesses on social commerce platforms in Bangkok, Thailand. The study considers both internal and external factors, including but not limited to business characteristics and location. Moreover, this research also analyzes the effects of employing multiple social commerce platforms on business efficiency and explores the underlying reasons for such effects. Research design, data, and methodology: Restaurants can be classified into different price ranges: low, medium, and high. To further investigate, we employed natural language processing AI to analyze online reviews and evaluate algorithm performance using machine learning techniques. We aimed to develop a model to gauge customer satisfaction with restaurants across different price categories effectively. Results: According to the research findings, several factors significantly impact restaurant groups in the low and mid-price ranges. Among these factors are population density and the number of seats at the restaurant. On the other hand, in the mid-and high-price ranges, the price levels of the food and drinks offered by the restaurant play a crucial role in determining customer satisfaction. Furthermore, the correlation between different social commerce platforms can significantly affect the business performance of high-price range restaurant groups. Finally, the level of online review sentiment has been found to influence customer decision-making across all restaurant types significantly. Conclusions: The study emphasizes that restaurants' characteristics based on their price level differ significantly, and social commerce platforms have the potential to affect one another. It is worth noting that the sentiment expressed in online reviews has a more significant impact on customer decision-making than any other factor, regardless of the type of restaurant in question.

• Asia pacific journal of information systems
• /
• v.31 no.4
• /
• pp.472-490
• /
• 2021

The detection of products with manipulated reviews has received widespread research attention, given that a truthful, informative, and useful review helps to significantly lower the search effort and cost for potential customers. This study proposes a method to recognize products with manipulated online customer reviews by examining the sequence of each review's sentiment, readability, and rating scores by product on randomness, considering the example of a Russian online retail site. Additionally, this study aims to examine the association between brand awareness and existing manipulation with products' reviews. Therefore, we investigated the difference between well-known and unknown brands' products online reviews with and without manipulated reviews based on the average star rating and the extremely positive sentiment scores. Consequently, machine learning techniques for predicting products are tested with manipulated reviews to determine a more useful one. It was found that about 20% of all product reviews are manipulated. Among the products with manipulated reviews, 44% are products of well-known brands, and 56% from unknown brands, with the highest prediction performance on deep neural network.

• International Commerce and Information Review
• /
• v.10 no.1
• /
• pp.279-293
• /
• 2008

The number of participants in an online dispute resolution(ODR) system is crucial to its survival. Securing participation is nonetheless difficult. Clearly, it is important to offer a system that is fair, transparent and offers an efficient service at low cost. These factors are fundamental to ensure trust and to build a returning customer base to the system, but are not what attracts a party to submit a dispute for settlement. This paper describes and discusses four main categories of legal measures found in the online dispute resolution services offered by SquareTrade and WIPO. In spite of shortcomings in the offered, the legal measures have contributed to attract large numbers of participants. Large participation secures the long-term economic viability of an online dispute resolution system. The four categories of legal measures described and discussed in this paper need to be part of the specifications and the design and development of future ODR system.

• Journal of Information Technology Services
• /
• v.11 no.3
• /
• pp.103-127
• /
• 2012

With the advent of SNS (Social Network Services), the product reviews by friends in SNS are intensively utilized for online marketing. However, there is a lack of empirical evidence on the actual marketing effect of SNS reviews, although we need to identify who can be the target of SNS marketing in terms of customer attributes, preferences, or experiences. In this study, we investigate the moderating role of customer attributes in identifying the effect of SNS reviews on customer purchasing decision. As the moderating variables, we adopt 'information search experience' and 'perception of information overload'. Research results evidence that, in order to understand the effect of SNS reviews in a comprehensive manner, we need to examine it in the context of various related factors such as 'information search experience' and 'perception of information overload'. The results show that the persuading effect of SNS reviews for product purchasing is stronger for the customers with the lower information search experiences as well as the lower perception on the information overload on the web. This result delivers managerial implications on who can be the target customers of SNS marketing.

• Journal of Korean Society for Quality Management
• /
• v.48 no.3
• /
• pp.421-431
• /
• 2020

Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

• International Commerce and Information Review
• /
• v.10 no.1
• /
• pp.51-72
• /
• 2008

Recently, CRM has been integrated with e-CRM based on information and technology and its introduction is increasing. In particular, as a-CRM effectively collects information of customers with low cost and consolidates relations with customers through interactions with them, it is easier to achieve the marketing goals of companies. This study examines theories of CRM and a-CRM, and discusses development plan for successful introduction of e-CRM based on case studies on its introductions. Political suggestions are presented as follows: First, the basic rule to manage customers in respect to e-CRM is customer-oriented management. For optimal customer management, various customer service channels that support customers in real world as well as online should be provided for the best e-CRM system. Second, of increasing online customers, important customers should be sorted out for which individualized services should be provided and if so, they can be faithful customers. It is believed to be a true development direction of e-CRM appropriate to current society. With introduction of e-CRM, values and needs of customers should be analysed through various sorts of communication and information activities, and segmental marketing activities should be developed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.1
• /
• pp.133-140
• /
• 2011

For both customers and companies, it is very important to analyze online customer reviews, which consist of small documents that include opinions or experiences about products or services, because the customers can get good informations and the companies can establish good marketing strategies. In this paper, we propose the association model for the opinion mining which can analyze customer opinions posted on web. The association model is to modify the association rules mining model in data mining in order to apply efficiently and effectively the association mining techniques to the opinion mining. We designed and implemented the opinion mining systems based on the modified association model and the grouping idea which would enable it to generate significant rules more.

• Journal of Internet Computing and Services
• /
• v.18 no.2
• /
• pp.75-85
• /
• 2017

Open innovation, a new paradigm which utilizes customer ideas for organizational innovation directly, is evaluated as a useful method to innovate the organization itself. In this research, we analyze the case of Starbucks' online community, MyStarbucksIdea.com to examine how collective intelligence is formed out of mass customers in the community and how open innovation is to be implemented successfully. We review various challenges in implementing open innovation and then suggest practical approaches to the challenges, including customer relationship management, utilization of opinion leaders, application of engineering techniques, etc.