• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.15-28
• /
• 2022

Due to recent expansion of online market such as clothing, utilizing customer review has become a major marketing measure. User review has been used as a tool of analyzing sentiment of customers. Sentiment analysis can be largely classified with machine learning-based and lexicon-based method. Machine learning-based method is a learning classification model referring review and labels. As research of sentiment analysis has been developed, multi-modal models learned by images and video data in reviews has been studied. Characteristics of words in reviews are differentiated depending on products' and customers' categories. In this paper, sentiment is analyzed via considering review data and metadata of products and users. Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Self Attention-based Multi-head Attention models and Bidirectional Encoder Representation from Transformer (BERT) are used in this study. Same Multi-Layer Perceptron (MLP) model is used upon every products information. This paper suggests a multi-modal sentiment analysis model that simultaneously considers user reviews and product meta-information.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.311-328
• /
• 2022

Because of the spread of smartphones due to the development of information and communication technology, online shopping mall services can be used on computers and mobile devices. As a result, the number of users using the online shopping mall service increases rapidly, and the types of products traded are also growing. Therefore, to maximize profits, companies need to provide information that may interest users. To this end, the recommendation system presents necessary information or products to the user based on the user's past behavioral data or behavioral purchase records. Representative overseas companies that currently provide recommendation services include Netflix, Amazon, and YouTube. These companies support users' purchase decisions by recommending products to users using ratings, purchase records, and clickstream data that users give to the items. In addition, users refer to the ratings left by other users about the product before buying a product. Most users tend to provide ratings only to products they are satisfied with, and the higher the rating, the higher the purchase intention. And recently, e-commerce sites have provided users with the ability to vote on whether product reviews are helpful. Through this, the user makes a purchase decision by referring to reviews and ratings of products judged to be beneficial. Therefore, in this study, the correlation between the product rating and the helpful information of the review is identified. The valuable data of the evaluation is reflected in the recommendation system to check the recommendation performance. In addition, we want to compare the results of skipping all the ratings in the traditional collaborative filtering technique with the recommended performance results that reflect only the 4 and 5 ratings. For this purpose, electronic product data collected from Amazon was used in this study, and the experimental results confirmed a correlation between ratings and review usefulness information. In addition, as a result of comparing the recommendation performance by reflecting all the ratings and only the 4 and 5 points in the recommendation system, the recommendation performance of remembering only the 4 and 5 points in the recommendation system was higher. In addition, as a result of reflecting review usefulness information in the recommendation system, it was confirmed that the more valuable the review, the higher the recommendation performance. Therefore, these experimental results are expected to improve the performance of personalized recommendation services in the future and provide implications for e-commerce sites.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.29-39
• /
• 2020

Online communities, such as Internet portal sites and social media, have become popular since they allow users to share opinions and to obtain information anytime, anywhere. Accordingly, an increasing number of opinions are manipulated to the advantage of particular groups or individuals, and these opinions include falsified product reviews and political propaganda. Existing detection systems are built upon the characteristics of manipulated opinions for one particular time period. However, manipulation tactics change over time to evade detection systems and to more efficiently spread information, so detection systems should also evolve according to the changes. We therefore propose a system that helps observe and trace changes in manipulation tactics. This system classifies opinions into clusters that represent different tactics, and changes in these clusters reveal evolving tactics. We evaluated the system with over a million opinions collected during three election campaigns and found various changes in (i) the times when manipulations frequently occur, (ii) the methods to manipulate recommendation counts, and (iii) the use of multiple user IDs. We suggest that the operators of online communities perform regular audits with the proposed system to identify evolutions and to adjust detection systems.

• International Journal of Costume and Fashion
• /
• v.11 no.2
• /
• pp.65-78
• /
• 2011

Social media which support to share information and communicate between online users have recently won great popularity. Of the various social services blogs have played an active role as a community in sharing delivering and exchanging information among individual users who have share similar opinions hobbies and preferences. Based on this cultural phenomenon some companies often take advantage of blogs as a marketing tool to strengthen their public relations or deliver particular information to their costumer. This study is designed to classify fashion-related blogs and define the characteristics of each type expecting significant influences on future studies on this topic. We selected 50 fashion-related blogs as subjects including 25 Korean blogs and the same number of international blogs, defined their characteristics and classified them into four different types. As the result we found that there are apparent differences between the four types of blogs: "Individual taste" blogs which noticeably reflect bloggers' own preference "Trend leader" blogs in which the bloggers intend to be trend leaders beyond expressing their preference "Fashion media" blogs which plays a significant role as a magazine by providing various information concerning fashion for costumers and "Sales promotion" blogs which are used as promotional materials to attract customers by providing product reviews or advertisements.

• Asia pacific journal of information systems
• /
• v.27 no.3
• /
• pp.139-155
• /
• 2017

As social media are increasingly being used as a marketing platform, electronic word-of-mouth (eWOM) has also become popular in both research and business areas. However, although many studies have examined the effect of eWOM, the products investigated in most of these studies, such as films or books, are not likely to be consumed daily. Therefore, in this study, we analyze the effect of eWOM on low involvement products, which are inexpensive and enough for everyday spending. Given that low involvement products have unique characteristics such as low price, we conduct an experiment using a real sales dataset related to soft drinks. We also analyze the effect of eWOM in two social media platforms. We find that eWOM influences the sales of low involvement products, but such influence is dependent on the characteristic of the social media platform. Based on these results, we suggest that marketers and retailers selling low involvement products must consider eWOM, such as reviews, and differentiate their strategies based on their focused social media platform.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.9
• /
• pp.1153-1158
• /
• 2018

Online customer evaluations and social media information among a variety of information sources are critical for businesses as it influences the customer's decision making. There are limitations on the time and money that the survey will ask to identify a variety of customers' needs and complaints. The customer review data at online shopping malls provide the ideal data sources for analyzing customer sentiment about their products. In this study, we collected product reviews data on the smartphone of Samsung and Apple from Amazon. We applied five classification algorithms which are used as representative sentiment analysis techniques in previous studies. The five algorithms are based on support vector machines, bagging, random forest, classification or regression tree and maximum entropy. In this study, we proposed entropy score which can comprehensively evaluate the performance of classification algorithm. As a result of evaluating five algorithms using an entropy score, the SVMs algorithm's entropy score was ranked highest.

• Journal of Information Technology Applications and Management
• /
• v.27 no.6
• /
• pp.53-73
• /
• 2020

Many prior studies have been conducted that positive reviews increase the intention to purchase. However, there are very few papers that have studied the impact of review search on purchase satisfaction. It is meaningful to study the impact of review search on purchase satisfaction as it can lead the business successfully by inducing repurchase. There is also no study of how review search have different effects on purchase satisfaction among countries. Given the growing number of cross-border e-commerce, we believe that the need for research is high because identifying these differences between countries can have a very important impact on a company's successful overseas expansion. Therefore, in this study, the impact of positive and negative review search on purchase satisfaction and the national impact were set up as a research model. In order to verify this research model, the survey was distributed to those who experienced online purchase in Korea and China, and a total of 234 copies were collected, including 125 copies in Korea, 109 copies in China, and the research model was verified using Smart-PLS structural equation analysis tools. First, positive review search has been shown to positively affect purchase satisfaction. Second, it has been shown that negative review search also has a positive effect on purchase satisfaction. Third, the impact of positive and negative review search on purchase satisfaction was different between Korea and China. While Korea is more aggressive in review search than China due to its high tendency to avoid uncertainty, China is less likely to avoid uncertainty than Korea and is more likely to rely on brand familiarity. Therefore, according to the uncertainty avoidance moderation effect the impact of positive and negative review search on purchase satisfaction was higher in Korea than in China. In this study, Shopping mall managers need to take strategic measures to maximize shopping mall performance by recognizing positive aspects of negative review search on purchase satisfaction. Companies and managers in Korea and China can establish strategies to promote product sales when companies enter the global market.

• Management & Information Systems Review
• /
• v.37 no.2
• /
• pp.23-42
• /
• 2018

As the development of the Internet in China has led to the active shopping of the internet, the number of Chinese internet users and online shopping malls is increasing rapidly. Chinese internet shopping malls are experiencing satisfaction and discontent with their websites. Research has focused on the satisfaction of customers using internet shopping malls and internet shopping malls reported complaints to users as complaints about products and websites. The study looked at seven area Chinese internet users (Beijing, Harbin, Shenyang, Ganssu, Xian, Shanghai and Henan). The effect of product complaints and site complaints on shopping attitudes and behaviors of internet shopping users was studied, and economic benefits were studied as a control variable. As a result, There was no effect on controlling the economic benefits of the complaint against the product, but the controlling the economic benefits of the complaint on the site was effect. About 83 percent of those surveyed were in their 20s and 30s who had experience shopping online and in internet. And It is intended to present theoretical reviews and guidelines for Korean internet shopping malls operating here, as they plan to expand to China by analyzing their internet shopping mall users.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.193-205
• /
• 2021

The AI speaker market is growing steadily. However, the satisfaction of actual users is only 42%. Therefore, in this paper, we collected reviews on Amazon Echo Dot 3rd and 4th generation models to analyze what hinders the user experience through the topic changes and emotional changes of each generation of AI speakers. By using topic modeling analysis techniques, we found changes in topics and topics that make up reviews for each generation, and examined how user sentiment on topics changed according to generation through deep learning-based sentiment analysis. As a result of topic modeling, five topics were derived for each generation. In the case of the 3rd generation, the topic representing general features of the speaker acted as a positive factor for the product, while user convenience features acted as negative factor. Conversely, in the 4^th generation, general features were negatively, and convenience features were positively derived. This analysis is significant in that it can present analysis results that take into account not only lexical features but also contextual features of the entire sentence in terms of methodology.

• Journal of Korean Home Economics Education Association
• /
• v.22 no.3
• /
• pp.129-145
• /
• 2010

In this study, when buying fashion products through internet shopping malls, it is researched about the buying behavior, the awareness of customer review, the use and posting of customer review and the accompanying awareness. The difference of awareness on the customer review according to their involvement of clothes, are examined from high school students in Seoul. And it is examined if they experienced any dissatisfaction after their purchase and what their behavior were. The questionnaire survey was taken by 508 students from 6 high schools in Seoul. The average, the standard deviation, the frequency, the t-test, the One way ANOVA and Duncan's Multiple Test were conducted for data analysis using SPSS 17.0. In the fashion products purchase behavior of the students, The reasons of buying were mainly because of the diversity and the convenience. Some students don't shop online because screen product and actual product are not the same. The awareness of the customer review represented high in the reliability and usefulness. The awareness on the influence of the customer review represented high in the contents direction and the numbers of the customer reviews but represented low in the timeliness. As to the awareness of the customer review, the student using it represented higher in all elements such as the usefulness, the reliability, and the influence than students who not use customer review. The students posting customer review recognized higher on the usefulness and the reliability of the customer review than those who did not post it, and were highly influenced by the numbers of customer reviews. The awareness of the customer review according to the involvement of clothes was the difference only in the usefulness. As to coping actions of students experiencing dissatisfaction, the proportion of the students coping with the public action and those who do not perform any action represented high.