• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.

• Journal of Korea Trade
• /
• v.24 no.8
• /
• pp.39-62
• /
• 2020

Purpose - Korean exports account for a vast proportion of Korean GDP, and large volumes of Korean products are sold in the United States. Identifying and characterizing actual and potential product hazards related to Korean products is critical to safeguard Korean export trade, as severe quality issues can impair Korea's reputation and reduce global consumer confidence in Korean products. In this study, we develop country-of-origin-based product risk analysis methods for social media with a specific focus on Korean-labeled products, for the purpose of safeguarding Korean export trade. Design/methodology - We employed two social media datasets containing consumer-generated product reviews. Sentiment analysis is a popular text mining technique used to quantify the type and amount of emotion that is expressed in the text. It is a useful tool for gathering customer opinions regarding products. Findings - We document and discuss the specific potential risks found in Korean-labeled products and explain their implications for safeguarding Korean export trade. Finally, we analyze the false positive matches that arise from the established dictionaries that were used for risk discovery and utilize these classification errors to suggest opportunities for the future refinement of the associated automated text analytic methods. Originality/value - Various studies have used online feedback from social media to analyze product defects. However, none of them links their findings to trade promotion and the protection of a specific country's exports. Therefore, it is important to fill this research gap, which could help to safeguard export trade in Korea.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.6
• /
• pp.1069-1086
• /
• 2013

Nowadays, web defacement becomes the utmost threat which can harm the target organization's image and reputation. These defacement activities reflect the hacker's political motivation or his tendency. Therefore, the analysis of the hacker's activities can give the decisive clue to pursue criminals. A specific message or photo or music on the defaced web site and the outcome of analysis will be supplying some decisive clues to track down criminals. The encoding method or used fonts of the remained hacker's messages, and hacker's SNS ID such as Twitter or Facebook ID also can help for tracking hackers information. In this paper, we implemented the web defacement analysis system by applying CBR algorithm. The implemented system extracts the features from the web defacement cases on zone-h.org. This paper will be useful to understand the hacker's purpose and to plan countermeasures as a IDSS(Investigation Detection Support System).

• The Journal of the Korea Contents Association
• /
• v.19 no.5
• /
• pp.194-204
• /
• 2019

The mobile payment app market has been expanding recently. However, the usage rate of mobile payment apps is not meeting service providers' expectations due to concerns about security and privacy. This study investigated how personal predisposition and how the security signals of the payment app affect users' perceived privacy and security risks, and how these factors ultimately affect the trust of mobile payment apps. The results showed that privacy concerns increase the risk of perceived personal information leaks and reduce perceived mobile system security, while familiarity, perceived reputation, and assurance seal reduce the risk of perceived personal information leaks and increase perceived mobile system security. Finally, it revealed that the reduced risk of perceived personal information leaks and the increased security of mobile systems had a positive impact on the reliability of mobile payment apps.

• Journal of Communications and Networks
• /
• v.17 no.1
• /
• pp.75-83
• /
• 2015

In mobile ad-hoc networks (MANETs), nodes are mobile in nature. Collaboration between mobile nodes is more significant in MANETs, which have as their greatest challenges vulnerabilities to various security attacks and an inability to operate securely while preserving its resources and performing secure routing among nodes. Therefore, it is essential to develop an effective secure routing protocol to protect the nodes from anonymous behaviors. Currently, game theory is a tool that analyzes, formulates and solves selfishness issues. It is seldom applied to detect malicious behavior in networks. It deals, instead, with the strategic and rational behavior of each node. In our study,we used the dynamic Bayesian signaling game to analyze the strategy profile for regular and malicious nodes. This game also revealed the best actions of individual strategies for each node. Perfect Bayesian equilibrium (PBE) provides a prominent solution for signaling games to solve incomplete information by combining strategies and payoff of players that constitute equilibrium. Using PBE strategies of nodes are private information of regular and malicious nodes. Regular nodes should be cooperative during routing and update their payoff, while malicious nodes take sophisticated risks by evaluating their risk of being identified to decide when to decline. This approach minimizes the utility of malicious nodes and it motivates better cooperation between nodes by using the reputation system. Regular nodes monitor continuously to evaluate their neighbors using belief updating systems of the Bayes rule.

• International Commerce and Information Review
• /
• v.1 no.1
• /
• pp.179-201
• /
• 1999

CALS/EC is about doing business electronically. It is based on the electronic processing and transmission of data, including text, sound and video. It encompasses many diverse activities including electronic trading of goods and services, online delivery of digital content, electronic fund transfers, electronic share trading, electronic bills of lading, commercial auctions, collaborative design and engineering, online sourcing, public procuremet, direct consumer marketing, and after-sales service. It involves both products(e.g. consumer goods, specialised medical equipment) and services(e.g. information services, financial and legal services); traditional activities(e.g. healthcare, education) and new activities (e.g. virtual malls). CALS/EC will be emerging to replace and substitute the role of the conventional market. By changing and eliminating some processes of the transactions, the electronic market and the electronic commerce will redistribute the power and hence the benefits of the market activities. Traditional way of doing business may enter into the new electronic market because the role and function of trust and established reputation will be reinforced in the electronic market. The CALS/EC through the Internet has been in the spotlight in the shopping behavior of the consumers. Accordingly Corporates are trying to adapt themselves to those rapidly changing environments being affected by the Internet. Among others, particularly to be noted is the CALS/EC between corporations and consumers whose potential growth can be considered very substantial. This report, focusing on the introduction of CALS/EC for the logistics of SMEs, will allow us to prepare more efficiently for the coming 21st Century. It is obvious that CALS/EC is fast becoming the useful way of exchanging not only information but products in business between firm-to-firm and firm-to-customer.

• CRM연구
• /
• v.1 no.1
• /
• pp.23-48
• /
• 2006

Internet B2C marketplace such as 'Auction', 'G Market', 'Daum onket' etc.(called open market) has grown sharply in sales about yearly 100% rate increase in recent 1-2 years in Korea. Although Open marketplace has much reputation and the customer loyalty, almost of merchants participated in open market, which size in sales are medium/small, has poor reputation and trust. Consumers, who have to get in touch with untrustworthy merchants for trade in openmarket, perceive high trade risk which undergo the monetary damages such as 'merchandise never received'. This examines what factors consumer trust develop in online marketplace. This study explores several perceived risk factors in an open market by factor analysis and multi-regression to prove the relationships between the degree of trust for the merchants and the perceived trade risk. 133 data collected from the open market user data in this survey. In this study, the consumer's trade satisfaction in open market is low by 4.2 point degree of 7 point likert scale. and perceives 4 trade risk factors such as (1) 'failure to honor warranty or guarantee' (2) 'defective/poor goods in quality' (3) 'merchandise never received or received late' (4) 'poor information'. the degree of merchant's trust has significant relationship with the degree of perceived risk(sig. = 0.0000, $R^2=.327$) We find that the open market has to enhance the relationship marketing of trust by developing the strategies.

• Korea Journal of Hospital Management
• /
• v.6 no.3
• /
• pp.5-24
• /
• 2001

The purpose of this study was to serve as a basis for providing quality medical service and mapping out consumer-centered marketing strategies to successfully cope with the rapidly changing medical environment and meet consumer needs, by examining what affected the satisfaction and revisit of health Promotion center Client. The subjects in this study were 186 of visitor to health Promotion center in a university hospital in the city of Busan. A survey was conducted with structured questionnaire from March 2 to 30, 2001. The collected data were analyzed with SPSS for Windows (ver10.0). For more statistical analysis, frequency analysis, component analysis, t-test, ANOVA and correlation analysis procedures were utilized. Results of the study can be summarized as follows: 1. Regarding demographic characteristics, 51.6% of the Client investigated were male, and 48.4% were female. The greatest number of them were in their 40s(38.9%). 86.5% were married, and 34.2% were self-employed. 44% were a high-school graduate, and the monthly mean income of 59.4% was one to three million Won. And, the residential area of 46.8%, the largest percentage, was a half-an-hour distance from health Promotion center. 2. The most common motivation of their selection of the health Promotion center was a recommendation by Staff and neighborhood(59.7%), followed by excellent facilities and services(17.2%), the tradition and reputation of the hospital(7.5%), and its publicity pamphlets(7.5%). 3. 45.9%, the largest percentage, acquired health-related information from their friends or acquaintances. 43.8%, the greatest percentage, visited there because they felt there's something wrong with their body. 53.4% worried about the possibility of being attacked by cancer, and 57.5% wanted to take a precise cancer examination. For health maintenance, 50.1% got regular exercise. Regular exercise was considered most crucial for health maintenance or promotion. 4. The largest reason they used that examination center again was the kindness of employees(52.7%), followed by the tradition and reputation of the hospital(21%) and excellent examination setting and equipment(10.8%). 5. By demographic factor, there was no significant difference between the man and women in satisfaction level with examination and expenses. The women expressed more satisfaction at facilities, and the high-school graduate group were more contented with expenses. 6. As a result of investigating their satisfaction level according to the motivation of selecting that examination center, the group that chose the center due to excellent facilities and services were more satisfied with examination and expenses. 7. As for the relationship of total examination satisfaction to revisit. intention, there was a higher correlational relationship between total health examination satisfaction and expense satisfaction. Especially, the more they were satisfied with examination, the more they were willing to revisit there for another examination.

• Journal of Information Technology Services
• /
• v.14 no.1
• /
• pp.1-21
• /
• 2015

Recently, many companies have launched a new business model related to the mobile gift service in order to achieve or sustain a competitive advantage in the fast-growing mobile market. Due to the well combination of mobile technology advantages and offline gift-giving motivations, a mobile gift service has been proliferating over recent years. Although the motivation of mobile gift purchasing behavior can be different from that of offline gift purchasing behavior, there is still a lack of research on what factors are influencing and how they are impacting mobile gift purchasing behavior under diverse gift-giving settings. Therefore, based on both exchange and motivation theories as well as literature review, this study identified three influencing factors-economic (immediate rewards, convenience), social (friendship needs, reputation), and personal (enjoyment, self-satisfaction) benefits-and validated their impacts on intention to repurchase a mobile gift. Moreover, the moderating roles of intimacy and gift price in the relationships between benefits and mobile gift repurchasing intention were examined. The results provide many implications for marketing managers on how to enhance consumers' intention to repurchase, which in turn leads to sales and increased profit.

• Journal of Information Technology Services
• /
• v.12 no.4
• /
• pp.267-287
• /
• 2013

As the online bookstore market has been saturated and the level of competition has become more intense, maintaining competitive advantage by mitigating consumers' perceived risks can be considered as one of good alternative strategies a company should use. Although studies that identify the types of consumers' perceived risks in the context of online bookstores as well as validate the relationships between perceived risk and its antecedent/consequent factors in an integrated manner are strongly required, there has been less attention paid to these matters. Therefore, based on previous literature, we identify five types of perceived risks (financial, performance, online payment, delivery, and seller's response risk) and validate the impacts of online bookstore specific characteristics and user specific characteristics on perceived risk. In addition, we also verify causal relationship between perceived risk and intention to use online bookstores. The results of PLS test using 108 samples collected from undergraduate and graduate students confirm that perceived risk has a negative impact on intention to use and four antecedents (reputation, service quality, self-efficacy, and user experience) are significantly related to perceived risk.