• Journal of Information Technology Services
• /
• v.16 no.3
• /
• pp.113-125
• /
• 2017

Customers have been affected by others' opinions when they make a purchase. Thanks to the development of technologies, people are sharing their experiences such as reviews or ratings through online or social network services, However, although ratings are intuitive information for others, many reviews include only texts without ratings. Also, because of huge amount of reviews, customers and companies can't read all of them so they are hard to evaluate to a product without ratings. Therefore, in this study, we propose a methodology to predict ratings based on reviews for a product. In a methodology, we first estimate the topic-review matrix using the Latent Dirichlet Allocation technic which is widely used in topic modeling. Next, we predict ratings based on the topic-review matrix using the artificial neural network model which is based on the backpropagation algorithm. Through experiments with actual reviews, we find that our methodology can predict ratings based on customers' reviews. And our methodology performs better with reviews which include certain opinions. As a result, our study can be used for customers and companies that want to know exactly a product with ratings. Moreover, we hope that our study leads to the implementation of future studies that combine machine learning and topic modeling.

• Journal of Information Technology Services
• /
• v.15 no.2
• /
• pp.169-184
• /
• 2016

Smartphone use is rapidly spreading due to the advantage of being able to connect to the Internet anytime, anywhere--and mobile app development is developing accordingly. The characteristic of the mobile app market is the ability to launch one's app into foreign markets with ease as long as the platform is the same. However, a large amount of prior research asserts that consumers behave differently depending on their culture and, from this perspective, various studies comparing the differences between consumer behaviors in different countries exist. Accordingly, this research, which uses online product reviews (OPRs) in order to analyze the cultural differences in consumer behavior comparatively by nationality, proposes to compare the U.S. and South Korea by selecting ten apps which were released in both countries in order to perform a sentimental analysis on the basis of star ratings and, based on those ratings, to interpret the sentiments in reviews. This research was carried out to determine whether, on the basis of ratings analysis, analysis of review contents for sentiment differences, analysis of LDA topic modeling, and co-occurrence analysis, actual differences in online reviews in South Korea and the U.S. exist due to cultural differences. The results confirm that the sentiments of reviews for both countries appear to be more negative than those of star ratings. Furthermore, while no great differences in high-raking review topics between the U.S. and South Korea were revealed through topic modeling and co-occurrence analyses, numerous differences in sentiment appeared-confirming that Koreans evaluated the mobile apps' specialized functions, while Americans evaluated the mobile apps in their entirety. This research reveals that differences in sentiments regarding mobile app reviews due to cultural differences between Koreans and Americans can be seen through sentiment analysis and topic modeling, and, through co-occurrence analysis, that they were able to examine trends in review-writing for each country.

• Informatization Policy
• /
• v.28 no.4
• /
• pp.19-35
• /
• 2021

The purpose of this research is to investigate the attributes of the online world and to analyze their influence on democracy. The research focuses on the mayoral by-elections that were held in Seoul and Busan, South Korea, on April 4, 2021. The study demonstrates the characteristics of online spaces and the polarization of the online public through news articles and user comments from the Internet. The research includes topic modeling to measure the diversity of media reports, sentiment analysis to measure online public opinion, and interrupted time series analysis to understand how a particular event influences online attitudes. A combination of these methods is used to attempt to estimate the strength of political polarity in the online environment. The study shows diverse media reports by election region and candidate, where the online public repeatedly reveals high negative and low positive attitudes towards each candidate. Moreover, political polarity can differ based on the level of interest in an election. Although voters pay less attention to a by-election than a presidential election, there is a solid political polarity in the online world. Hence, the research recommends preparing measures to alleviate the polarization as politics requires significant online participation.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.12
• /
• pp.267-274
• /
• 2020

The focus of this study is to investigate the mediating role of online market orientation on information capital readiness-business performance relationship. The construct of information capital readiness is rarely researched. The readiness here refers to the availability of information capital needed to support strategy execution. As quantitative research, this study employs the partial least squares structural equation modeling (PLS-SEM) to test the hypotheses. Data was collected using questionnaires from the owners/managers of the micro, small, and medium-sized enterprises (MSMEs) in the East Java Province, Indonesia. As many as 433 respondents had participated. The result indicates that information capital readiness directly and positively affects business performance. Further analysis reveals that online market orientation partially mediates information capital readiness-business performance relationship. In conclusion, this study suggests that the owners/managers of the MSMEs should improve their information capital readiness to support online market orientation strategy so that it can improve their business performance. This is the first study that brings together the issues of information capital readiness and online market orientation as the antecedents of business performance in the Indonesian MSMEs research setting. The mediating role of online market orientation is rarely explored in previous studies.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.4
• /
• pp.249-260
• /
• 2019

The study examines the impact of financial risk, convenience risk, non-delivery risk; return policy risk and product risk on online consumer behavior of Malaysian consumers. The research employed a self-administered survey to collect empirical data from 245 Malaysian online shoppers by using convenience sampling. Cronbach alpha was calculated to confirm the reliability of the data and then normality was assessed. Confirmatory Factor Analysis was then conducted to test the model using the goodness-of-fit tests. And finally, structural equation modeling is used to test the hypotheses and draw conclusions. IBM SPSS AMOS version 22.0 was utilized for data analysis. The research indicates that product risk, convenience risk, and return policy risk have a significant and positive impact on online shopping behavior. Financial risk is found to have insignificant and negative effects on consumer behavior. In addition, the non-delivery risk is found to have a significant and negative impact on online shopping behavior. The findings provide a useful model for measuring and managing perceived risk in online shopping which may result in an increase in participation of Malaysian consumers and reduce their cognitive deficiencies in the e-commerce environment. Several managerial implications are discussed along with the scope for future research.

• Journal of Distribution Science
• /
• v.18 no.9
• /
• pp.45-53
• /
• 2020

Purpose: This study aims at investigating consumers' choice in online food purchasing behavior and the impact on repurchase for fresh food delivery which has recently shown rapid growth in Korea. The study focuses on the user experience factors af fecting satisfaction and intention to continuously use the online food market. Research design, data and methodology: The survey was conducted by 309 people who had purchased fresh food online, and the analysis was conducted using SPSS and AMOS. Structural Equation Modeling was used for the analysis for the verification of hypotheses. The factors that consumers value when ordering fresh food delivery services were defined as system quality, service quality, commodity quality, brand characteristics, and economics from the preceding study and the relationship between satisfaction and willingness to repurchase was verified. Results: When consumers purchase fresh food online, system quality, product quality, brand characteristics, and economics have had a significant impact on satisfaction. Meanwhile, of the five optional attributes of consumers, only economic efficiency has been verified to have a statistically significant impact on repurchase intentions. Conclusions: The results of the study suggested factors that consumers consider important when ordering fresh food online, providing basic data for companies to develop related strategies.

• Journal of Fashion Business
• /
• v.21 no.6
• /
• pp.31-46
• /
• 2017

This study views the people's propensity to rely on others' evaluations as the interpersonal trust online despite a lack of personal interactions. Therefore, this study explores the underlying dimensions of interpersonal trust and examines how interpersonal trust influences trust in the e-tailer and behavioral intent. Data of 395 adults who had purchased apparel goods online were collected nationwide using an online questionnaire. Exploratory and confirmative factor analysis identified five underlying constructs of interpersonal trust online such as peer identification, ability, integrity, shared lifegoals, and benevolence. A structural equation modeling test was conducted to examine the relationships between interpersonal trust, trust in the e-tailer, and behavioral intent. Interpersonal trust influenced on trust in the e-tailer, specifically on trust in the e-tailer's competence which subsequently increased a customer's behavioral intent such as attitude toward the e-tailer and shopping intention. Although no direct effect of interpersonal trust on the behavioral intent was found, interestingly, the effects of the interpersonal trust on the e-tailer trust which derived the behavioral intent to purchase. This result suggests that marketers devise a more effective system and environment that can encourage the interpersonal trust between customers to build a strong trust in e-tailers. It also provides a theoretical framework of online trust in the way of classifying interpersonal trust and trust in e-tailers.

• The Journal of Information Systems
• /
• v.32 no.4
• /
• pp.95-118
• /
• 2023

Purpose This study employed the Technology Acceptance Model (TAM) to understand students' acceptance of online learning systems. Specifically, this study investigated the factors influencing the behavioral intention of South Korean major university students to use online learning systems for educational purposes in the period when their university life had largely returned to the state it was in before the COVID-19 pandemic. Design/methodology/approach This study examined the impact of four external factors: self-efficacy, personal innovativeness, perceived enjoyment, and system quality, on two TAM constructs: perceived ease of use and perceived usefulness. Additionally, this study explored how perceived ease of use and perceived usefulness affect the behavioral intention to use online learning systems. We conducted an online-based survey using a structured questionnaire. The data collected from the survey were then subjected to Structural Equation Modeling (SEM) analysis to test the study's hypotheses and examine the relationships among the various constructs. Findings The findings reveal that perceived usefulness and ease of use significantly influence students' behavioral intentions to use online learning systems. Furthermore, factors of self-efficacy, perceived enjoyment, and system quality positively affect perceived usefulness and ease of use. Notably, personal innovativeness impacts ease of use but not perceived usefulness.

• Journal of Korea Trade
• /
• v.25 no.1
• /
• pp.47-64
• /
• 2021

Purpose - This paper empirically analyzed the determinants of the online food market in Korea and Vietnam as representatives of the developed market and emerging market. The online food market can be regarded as having a high potential value. This study aims to suggest the appropriate implications for each developed market and emerging market by empirically comparing and analyzing customers' online food purchase determinants in the growth change of the online food market. Design/methodology - The empirical model of this study was established with the motif of the TAM+Trust model suggested by Nguyen et al.'s (2019) existing theoretical framework. Davis's (1989) TAM model was adopted to establish a framework related to the determinants that consumers would accept, for the online food purchasing method. Then, the trust variable is added to the framework which is regarded as an important effector especially in food related researches. In this study's comparative analysis, the multi-group structural equation modeling analysis was implemented. Findings - The main finding of this study can be summarized as that the moderating effect of nationality is significant. This means that there is an obvious difference between the developed online food market and the emerging online food market. In addition, as the growth of the online market changes, the significant determinants of consumers' attitudes and purchase intentions are somewhat different. However, the usefulness of online food purchasing methods and the trust of websites were analyzed as significant factors. Originality/value - Although the potential of the online food market is abundant, studies on the determinants of customer's attitude and purchase intention are insufficient. Moreover, comparative studies between countries have not been conducted in existing studies. Therefore, the research value of this paper can be explained in that it has suggested implications for the continued growth of the online food market.

• Journal of Distribution Science
• /
• v.21 no.2
• /
• pp.7-20
• /
• 2023

Purpose: With the unique feature of O2O, consumers are now able to check the profile of the services and products online and then consume them in offline venues or vice versa. This study provides motivation and practical implications about online-to-offline (O2O) distribution channels and investigates the relationship between economic values, service consistency and brand identity attractiveness in the O2O distribution channel. Then identify the impact of brand identity attractiveness on the performance (reputation and reuse intention). Research design, data, and methodology: Structural equation modeling (SEM) has been used to investigate the relationship between economic value and brand identity attractiveness, which affects the reputation and reuse intention of services in O2O. Results: Empirical results show the positive and significant impact of economic value and service consistency on brand identity attractiveness which results the positive and significant impact on performance (reputation and reuse intention) in O2O. Conclusion: In the O2O distribution channel, economic value is an important aspect for the attractive image and brand identity. On the other side, brand identity attractiveness is important for the bright future of O2O services, continuous growth, achieving the distinct goal, keeping good promises with customers, and a better reputation of O2O services in distribution channels.