• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.21-33
• /
• 2022

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.971-978
• /
• 2022

As a marketing method in a non-face-to-face society, the purpose of this study is to test how AR experience affects purchase intention in the process of consumers recognizing product information to purchase products and to secure the basis for the effectiveness of developing and introducing augmented reality functions in future product brand applications. Literary research methods and empirical research methods were used to verify the research purpose, and to measure this, an application of domestic tableware brand 'Odense', which implements augmented reality functions, was produced and used as an experimental tool. Also, a direct causal relationship was attempted by constituting a questionnaire by deriving a measurement scale for perceived usefulness, perceived ease, perceived pleasure, and purchase, which are factors of technology acceptance theory (TAM), and empirical analysis was conducted using the SPSS 25.0 statistical package to achieve the purpose of the study. As a result of the study, significant results were derived from all factors in the effect of perceived usefulness, ease, and pleasure on purchase intention, and several significant differences were found among factors according to gender, age, and internet shopping usage time in general characteristics. In conclusion, the user experience of the medium in which the augmented reality function is introduced in the information recognition stage of the product has a positive effect on purchase compared to the user experience of existing applications.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.289-305
• /
• 2023

The rapid increase in the use of mobile devices is changing consumers' online shopping behavior. However, the difference in the effect on the conversion rate according to the time when consumers switch from a small screen to a large screen has not been sufficiently studied. In addition, the differences in the effect of device conversion on purchase performance according to the characteristics of each country's infrastructure have not been sufficiently studied. Against this background, this study aims to analyze whether the timing of switching from mobile devices to PC devices and the country's mobile Internet penetration rate are moderating the positive effect of device switching on purchase performance. For empirical analysis, Google Merchandise Store data was collected and 101,466 data from 130 countries were analyzed with a multilevel model. As a result of the analysis, consumers' device switching (i.e., mobile to PC) had a positive effect when it occurred in the middle of the consumer journey. However, it was analyzed that when device switching occurred at the later stage of the consumer journey, it had a negative effect on purchase performance. In addition, it was analyzed that the higher the mobile Internet penetration rate, the weaker the positive effect of consumer device conversion on purchase performance.

• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.39-56
• /
• 2023

Due to restrictions on offline activities caused by COVID-19, the use of mobile applications is increasing along with interest in online shopping, which are non-face-to-face commerce. Accordingly, mobile applications and various industries are combined, and the number of cases of using mobile applications in the fashion industry is increasing. In this study, the effect of e-service quality of fashion mobile applications on user's flow, user satisfaction, and service loyalty was examined. To conduct this study, a survey of 274 people who experienced the 'ABLY' fashion mobile application was used for analysis to verify the hypothesis. As a result of the analysis, it was found that informativity and responsiveness among the e-service quality of fashion mobile applications had a positive (+) effect on flow. And it has been confirmed that informativity, reliability, and responsiveness affect user satisfaction. In addition, flow has a positive (+) (+) effect on user satisfaction, and user satisfaction has a positive (+) effect on service loyalty. However, among the e-service quality of fashion mobile applications, reliability did not have a positive (+) effect on flow. And ease of use did not have a positive (+) effect on both flow and user satisfaction. Finally, it was confirmed that flow did not directly affect service loyalty. Through this study, we intend to contribute to the establishment of marketing strategies for fashion mobile application users, who are increasing with the development of mobile technology, and provide practical implications for the post-COVID-19 era.

• Journal of Korean Home Economics Education Association
• /
• v.34 no.4
• /
• pp.77-92
• /
• 2022

Recently, digital transformation in the financial industry has been accelerated, and it has become an important task to improve the level of utilization of Internet banking by elderly consumers, who are vulnerable to Internet use. Accordingly, this study analyzed 3,101 respondents in their 60s or older from the 11th year of the Media Panel Survey to identify demographic, experiential, and psychological factors that affect the self-efficacy of elderly consumers' usage of Internet banking. The main research findings are as follows. First, gender, education, occupation, and income were identified as demographic variables. Second, the Internet shopping experience was identified as an experiential factor. Also, concerns about information security, digital literacy, and high will for problem-solving were identified as psychological factors. Third, as a result of the moderating effect analysis on whether the experiential and psychological factors have different influences according to the group divided into the 60s and 70s, the effect on self-efficacy in the usage of the Internet was classified by age. The results of this study will be able to enrich the discussions related to the intention to utilize technology among elderly consumers by empirically revealing that there are characteristics that cause differences in financial behavior even within one group called the elderly.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.2
• /
• pp.13-25
• /
• 2019

This study conducted individual in-depth interviews of tourists from Taiwan, Hong Kong and Thailand who visited Daegu. According to the analysis, Taiwan's target audience conducted an interview at the Chimac Festival in July 2018 at Duryu Park and was a university student as an individual female tourist. She got the information through SNS. The accommodation was guest house and medium and low cost hotel. The main tourist attractions included Seomun Market Night Market, Eworld and Dongseongno. The meals were Anjirang Gopchang and Galbijim in Dongin-dong. Next, the Hong Kong tourist interview was held in May 2018 at the Kwandeung Festival in Duryu Park, and was an individual tourist as a man. Lastly, an interview with a Thai tourist was held in April 2018 at the Donghwa Temple Cherry Blossom Festival in Palgongsan Mountain, and he purchased a travel agent product as a man. Participants of the tour in Daegu were interested in unusual experiences such as beauty, wedding, theme parks, and restaurants that are unique to Korea. What was disappointing was that there were not enough shopping facilities, such as duty free shops, and that the table in the restaurant was inconvenient, and that there were not enough signboards by language for foreigners.

• Journal of Service Research and Studies
• /
• v.13 no.1
• /
• pp.127-143
• /
• 2023

Currently, the domestic traditional market has not escaped the swamp of stagnation that began in the early 2000s despite various projects promoted by many related players such as the central government and local governments. In order to overcome the crisis faced by the traditional market, various R&Ds have recently been conducted on how to build a smart traditional market that combines information and communication technologies such as big data analysis, artificial intelligence, and the Internet of Things. This study analyzes various previous studies, users of traditional markets, and application cases of ICT technology in foreign traditional markets since 2012 and proposes a model to build a smart traditional market using ICT technology based on the analysis. The model proposed in this study includes building a traditional market metaverse that can interact with visitors, certifying visits to traditional markets through digital signage with NFC technology, improving accuracy of fire detection functions using IoT and AI technology, developing smartphone apps for market launch information and event notification, and an e-commerce system. If a smart traditional market platform is implemented and operated based on the smart traditional market platform model presented in this study, it will not only draw interest in the traditional market to MZ generation and foreigners, but also contribute to revitalizing the traditional market in the future.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.325-345
• /
• 2023

In the rapidly evolving domain of e-commerce, our study presents a cohesive approach to enhance customer satisfaction prediction from online reviews, aligning methodological innovation with practical insights. We integrate the RFE-SHAP feature selection with LDA topic modeling to streamline predictive analytics in e-commerce. This integration facilitates the identification of key features-specifically, narrowing down from an initial set of 28 to an optimal subset of 14 features for the Random Forest algorithm. Our approach strategically mitigates the common issue of overfitting in models with an excess of features, leading to an improved accuracy rate of 84% in our Random Forest model. Central to our analysis is the understanding that certain aspects in review content, such as quality, fit, and durability, play a pivotal role in influencing customer satisfaction, especially in the clothing sector. We delve into explaining how each of these selected features impacts customer satisfaction, providing a comprehensive view of the elements most appreciated by customers. Our research makes significant contributions in two key areas. First, it enhances predictive modeling within the realm of e-commerce analytics by introducing a streamlined, feature-centric approach. This refinement in methodology not only bolsters the accuracy of customer satisfaction predictions but also sets a new standard for handling feature selection in predictive models. Second, the study provides actionable insights for e-commerce platforms, especially those in the clothing sector. By highlighting which aspects of customer reviews-like quality, fit, and durability-most influence satisfaction, we offer a strategic direction for businesses to tailor their products and services.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.177-200
• /
• 2021

Recently, the use of prepaid electronic payments such as electronic wallets, digital currency and prepaid points is gradually increasing. Prepaid electronic payments has the characteristic of being used after charging first. This study empirically investigated the factors affecting the intention to use online charging in order to help improve the service that require prepaid recharge by applying transformed TAM. Since there are not many previous studies for the intention to use online charging, we extract factors through preceding researches for electronic cash and mobile easy payment. Also we analyze the intention to use online charging for transportation card users, focusing on the moderating effects. As a result of the study, it was found that 'convenience', 'ubiquity', and 'self-efficacy' among the independent variables had a positive (+) effect on mediation variable 'perceived usefulness'. 'Perceived usefulness' was analyzed to have a significant influence on the dependent variable 'usage intention'. According to users' gender, internet usage time, internet shopping frequency, online charging frequency and transportation card usage type, the moderating effect was significant on 'perceived usefulness' and 'usage intention'. As an implication, it was suggested that service improvement and differentiated marketing are needed in direction of increasing the usefulness of services. Additional research directions were proposed for services such as e-wallets, prepaid points and digital currencies by adding other factors and moderate variables.