• Information Systems Review
• /
• v.24 no.1
• /
• pp.1-19
• /
• 2022

Social media-based communication has become crucial part of our personal and official lives. Therefore, it is no surprise that social media sentiment analysis has emerged an important way of detecting potential customers' sentiment trends for all kinds of companies. However, social media sentiment analysis suffers from huge number of sentiment features obtained in the process of conducting the sentiment analysis. In this sense, this study proposes a novel method by using Bayesian Network. In this model MBFS (Markov Blanket-based Feature Selection) is used to reduce the number of sentiment features. To show the validity of our proposed model, we utilized online review data from Yelp, a famous social media about restaurant, bars, beauty salons evaluation and recommendation. We used a number of benchmarking feature selection methods like correlation-based feature selection, information gain, and gain ratio. A number of machine learning classifiers were also used for our validation tasks, like TAN, NBN, Sons & Spouses BN (Bayesian Network), Augmented Markov Blanket. Furthermore, we conducted Bayesian Network-based what-if analysis to see how the knowledge map between target node and related explanatory nodes could yield meaningful glimpse into what is going on in sentiments underlying the target dataset.

• Information Systems Review
• /
• v.21 no.2
• /
• pp.29-50
• /
• 2019

Social media is divided into Owned Media, operated by companies according to information sources, and Earned Media, which third parties produce contents. Social media research developing the logic that brand-related content in social media increases awareness of potential customers and positively changes brand attitudes, resulting in increased sales and business performance. However, there are limitations in previous researches that can not fully explain the difference of media synergy effect according to the information source of social media. it is very important for the consumer to integrate media management because consumers are more likely to choose appropriate media information for the information needed at each decision making stage. The purpose of this study is to analyze the effect of eWOM of review site and social media (owned media and earned media) on movie sales. To do this, we collected 3,589 review data from films released in 2017. The results of the study showed that eWOM of review site, social media (owned media and earned media) had a positive effect on movie sales. However, it was found that the effect of moderating eWOM of review site was different between the owned media and the earend media.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.93-107
• /
• 2014

In this paper, we report what we have observed with regard to user-perspective issue clustering based on multi-layered two-mode network analysis. This work is significant in the context of data collection by companies about customer needs. Most companies have failed to uncover such needs for products or services properly in terms of demographic data such as age, income levels, and purchase history. Because of excessive reliance on limited internal data, most recommendation systems do not provide decision makers with appropriate business information for current business circumstances. However, part of the problem is the increasing regulation of personal data gathering and privacy. This makes demographic or transaction data collection more difficult, and is a significant hurdle for traditional recommendation approaches because these systems demand a great deal of personal data or transaction logs. Our motivation for presenting this paper to academia is our strong belief, and evidence, that most customers' requirements for products can be effectively and efficiently analyzed from unstructured textual data such as Internet news text. In order to derive users' requirements from textual data obtained online, the proposed approach in this paper attempts to construct double two-mode networks, such as a user-news network and news-issue network, and to integrate these into one quasi-network as the input for issue clustering. One of the contributions of this research is the development of a methodology utilizing enormous amounts of unstructured textual data for user-oriented issue clustering by leveraging existing text mining and social network analysis. In order to build multi-layered two-mode networks of news logs, we need some tools such as text mining and topic analysis. We used not only SAS Enterprise Miner 12.1, which provides a text miner module and cluster module for textual data analysis, but also NetMiner 4 for network visualization and analysis. Our approach for user-perspective issue clustering is composed of six main phases: crawling, topic analysis, access pattern analysis, network merging, network conversion, and clustering. In the first phase, we collect visit logs for news sites by crawler. After gathering unstructured news article data, the topic analysis phase extracts issues from each news article in order to build an article-news network. For simplicity, 100 topics are extracted from 13,652 articles. In the third phase, a user-article network is constructed with access patterns derived from web transaction logs. The double two-mode networks are then merged into a quasi-network of user-issue. Finally, in the user-oriented issue-clustering phase, we classify issues through structural equivalence, and compare these with the clustering results from statistical tools and network analysis. An experiment with a large dataset was performed to build a multi-layer two-mode network. After that, we compared the results of issue clustering from SAS with that of network analysis. The experimental dataset was from a web site ranking site, and the biggest portal site in Korea. The sample dataset contains 150 million transaction logs and 13,652 news articles of 5,000 panels over one year. User-article and article-issue networks are constructed and merged into a user-issue quasi-network using Netminer. Our issue-clustering results applied the Partitioning Around Medoids (PAM) algorithm and Multidimensional Scaling (MDS), and are consistent with the results from SAS clustering. In spite of extensive efforts to provide user information with recommendation systems, most projects are successful only when companies have sufficient data about users and transactions. Our proposed methodology, user-perspective issue clustering, can provide practical support to decision-making in companies because it enhances user-related data from unstructured textual data. To overcome the problem of insufficient data from traditional approaches, our methodology infers customers' real interests by utilizing web transaction logs. In addition, we suggest topic analysis and issue clustering as a practical means of issue identification.

• Archives of design research
• /
• v.19 no.2 s.64
• /
• pp.53-62
• /
• 2006

E-mail has indeed developed from 'a means of instant communication' to an indispensable part of online marketing. Therefore, companies need to implement consistent customer management. Communication with customers and marketing through e-mail is a powerful way of communication and adapting one-to-one marketing strategies to customer trends, habits and taste preferences. Since setting accurate targets is especially important in the fashion industry, e-mail marketing is the most effective way to communicate with customers and one-to-one marketing constitutes a very important strategy. In this study, I will analyze this powerful one-on-one marketing tool, particularly actual e-mail messages sent by an Internet Shopping Mall from June 12 to July 30, 2005, examine the effect of these messages on sales growth and analyze actual feedback received. Regarding e-mail read rates broken down by age and gender, 1 found that females in their late twenties recorded the highest rate at 21.66% and their contribution to sales growth was recorded at 3.5% From actual sales records, found that 28.10% of total sales were attributable to people in their late twenties, showing that the age group that reads e-mails the most also buys the most. Regarding feedback by e-mail title, e-mails from the 'Casual' category seemed to be the most effective, in that most of these e-mails were read. Also, messages sent on Tuesdays were read the most, according to the feedback analysis by weekday. Section e-mails were read more often than regular e-mails. Regarding the view rate according to the time e-mails were sent, messages sent to females in their late twenties at two o'clock in the afternoon were read by 20.93% of recipients, recording the highest read rate. By offering informative content and practical tips, visitors will be attracted to the site and generate site traffic. Therefore, we can conclude that sending e-mail messages can greatly contribute to sales growth and e-mail marketing is very effective. Also, in order to make e-mail campaigns more effective and improve marketing results, we need to analyze actual results and apply our findings in future e-mail campaigns. With this, we get successful marketing results.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.59-87
• /
• 2014

In MIS field, the researches on payment services are focused on adoption factors of payment service using behavior theories such as TRA(Theory of Reasoned Action), TAM(Technology Acceptance Model), and TPB (Theory of Planned Behavior). The previous researches presented various adoption factors according to types of payment service, nations, culture and so on even though adoption factors of identical payment service were presented differently by researchers. The payment service industry relatively has strong path dependency to the existing payment methods so that the research results on the identical payment service are different due to payment culture of nation. This paper aims to suggest a successful adoption factor of noble payment service regardless of nation's culture and characteristics of payment and prove it. In previous researches, common adoption factors of payment service are convenience, ease of use, security, convenience, speed etc. But real cases prove the fact that adoption factors that the previous researches present are not always critical to success to penetrate a market. For example, PayByPhone, NFC based parking payment service, successfully has penetrated to early market and grown. In contrast, Google Wallet service failed to be adopted to users despite NFC based payment method which provides convenience, security, ease of use. As shown in upper case, there remains an unexplained aspect. Therefore, the present research question emerged from the question: "What is the more essential and fundamental factor that should takes precedence over factors such as provides convenience, security, ease of use for successful penetration to market". With these cases, this paper analyzes four cases predicted on the following hypothesis and demonstrates it. "To successfully penetrate a market and sustainably grow, new payment service should find non-customer of the existing payment service and provide noble payment method so that they can use payment method". We give plausible explanations for the hypothesis using multiple case studies. Diners club, Danal, PayPal, Square were selected as a typical and successful cases in each category of payment service. The discussion on cases is primarily non-customer analysis that noble payment service targets on to find the most crucial factor in the early market, we does not attempt to consider factors for business growth. We clarified three-tier non-customer of the payment method that new payment service targets on and elaborated how new payment service satisfy them. In case of credit card, this payment service target first tier of non-customer who can't pay for because they don't have any cash temporarily but they have regular income. So credit card provides an opportunity which they can do economic activities by delaying the date of payment. In a result of wireless phone payment's case study, this service targets on second of non-customer who can't use online payment because they concern about security or have to take a complex process and learn how to use online payment method. Therefore, wireless phone payment provides very convenient payment method. Especially, it made group of young pay for a little money without a credit card. Case study result of PayPal, online payment service, shows that it targets on second tier of non-customer who reject to use online payment service because of concern about sensitive information leaks such as passwords and credit card details. Accordingly, PayPal service allows users to pay online without a provision of sensitive information. Final Square case result, Mobile POS -based payment service, also shows that it targets on second tier of non-customer who can't individually transact offline because of cash's shortness. Hence, Square provides dongle which function as POS by putting dongle in earphone terminal. As a result, four cases made non-customer their customer so that they could penetrate early market and had been extended their market share. Consequently, all cases supported the hypothesis and it is highly probable according to 'analytic generation' that case study methodology suggests. We present for judging the quality of research designs the following. Construct validity, internal validity, external validity, reliability are common to all social science methods, these have been summarized in numerous textbooks(Yin, 2014). In case study methodology, these also have served as a framework for assessing a large group of case studies (Gibbert, Ruigrok & Wicki, 2008). Construct validity is to identify correct operational measures for the concepts being studied. To satisfy construct validity, we use multiple sources of evidence such as the academic journals, magazine and articles etc. Internal validity is to seek to establish a causal relationship, whereby certain conditions are believed to lead to other conditions, as distinguished from spurious relationships. To satisfy internal validity, we do explanation building through four cases analysis. External validity is to define the domain to which a study's findings can be generalized. To satisfy this, replication logic in multiple case studies is used. Reliability is to demonstrate that the operations of a study -such as the data collection procedures- can be repeated, with the same results. To satisfy this, we use case study protocol. In Korea, the competition among stakeholders over mobile payment industry is intensifying. Not only main three Telecom Companies but also Smartphone companies and service provider like KakaoTalk announced that they would enter into mobile payment industry. Mobile payment industry is getting competitive. But it doesn't still have momentum effect notwithstanding positive presumptions that will grow very fast. Mobile payment services are categorized into various technology based payment service such as IC mobile card and Application payment service of cloud based, NFC, sound wave, BLE(Bluetooth Low Energy), Biometric recognition technology etc. Especially, mobile payment service is discontinuous innovations that users should change their behavior and noble infrastructure should be installed. These require users to learn how to use it and cause infra-installation cost to shopkeepers. Additionally, payment industry has the strong path dependency. In spite of these obstacles, mobile payment service which should provide dramatically improved value as a products and service of discontinuous innovations is focusing on convenience and security, convenience and so on. We suggest the following to success mobile payment service. First, non-customers of the existing payment service need to be identified. Second, needs of them should be taken. Then, noble payment service provides non-customer who can't pay by the previous payment method to payment method. In conclusion, mobile payment service can create new market and will result in extension of payment market.

• Archives of design research
• /
• v.17 no.2
• /
• pp.77-86
• /
• 2004

User-Centered Design Approach plays important role in dealing with usability issues for developing modern technology products. Yet it is still questionable whether the User-Centered approach is enough for the development of successful consumer contents since the User-Centered Design is originated from the software engineering field where meeting customers' functional requirement is the most critical aspect in developing a software. However, modern consumer market is already saturated and in order to meet ever increasing consumer requirements, the User-Centered Design approach needs to be expanded. As a way of incorporating the User-Centered Approach into the consumer product development, Jordan suggested the 'Pleasure-based Approach' in industrial design field, which usually generates multi-dimensional user requirements: 1)physical, 2)cognitive, 3)identity and 4) social. It is the current tendency that many portal and community service providers focus on fulfilling both functional and emotional needs for users when developing new items, contents and services. Previously fulfilling consumers' emotional needs solely depend on visual designer's graphical sense and capability. However, taking the customer-centered approach on withdrawing consumers' unknown needs is getting critical in the competitive market environment. This paper reviews different types of user research techniques and categorized into 6 ways based on Kano(1992)'s product quality model. Based on his theory, only performance factors, such as suability, can be identified through the user-centered design approach. The user-centered design approach has to be expanded to include factors include personality, sociability, pleasure, and so on. In order to identify performance as well as excellent factors through user research, a user-research framework was established and tested through the case study, which is ' the development of new online service for teens '. The results of the user research were summarized at the end of the paper and the pros and cons of each research techniques were analyzed.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.19-43
• /
• 2014

The Pareto principle, also known as the 80-20 rule, states that roughly 80% of the effects come from 20% of the causes for many events including natural phenomena. It has been recognized as a golden rule in business with a wide application of such discovery like 20 percent of customers resulting in 80 percent of total sales. On the other hand, the Long Tail theory, pointing out that "the trivial many" produces more value than "the vital few," has gained popularity in recent times with a tremendous reduction of distribution and inventory costs through the development of ICT(Information and Communication Technology). This study started with a view to illuminating how these two primary business paradigms-Pareto principle and Long Tail theory-relates to the success of virtual knowledge collaboration. The importance of virtual knowledge collaboration is soaring in this era of globalization and virtualization transcending geographical and temporal constraints. Many previous studies on knowledge sharing have focused on the factors to affect knowledge sharing, seeking to boost individual knowledge sharing and resolve the social dilemma caused from the fact that rational individuals are likely to rather consume than contribute knowledge. Knowledge collaboration can be defined as the creation of knowledge by not only sharing knowledge, but also by transforming and integrating such knowledge. In this perspective of knowledge collaboration, the relative distribution of knowledge sharing among participants can count as much as the absolute amounts of individual knowledge sharing. In particular, whether the more contribution of the upper 20 percent of participants in knowledge sharing will enhance the efficiency of overall knowledge collaboration is an issue of interest. This study deals with the effect of this sort of knowledge sharing distribution on the efficiency of knowledge collaboration and is extended to reflect the work characteristics. All analyses were conducted based on actual data instead of self-reported questionnaire surveys. More specifically, we analyzed the collaborative behaviors of editors of 2,978 English Wikipedia featured articles, which are the best quality grade of articles in English Wikipedia. We adopted Pareto ratio, the ratio of the number of knowledge contribution of the upper 20 percent of participants to the total number of knowledge contribution made by the total participants of an article group, to examine the effect of Pareto principle. In addition, Gini coefficient, which represents the inequality of income among a group of people, was applied to reveal the effect of inequality of knowledge contribution. Hypotheses were set up based on the assumption that the higher ratio of knowledge contribution by more highly motivated participants will lead to the higher collaboration efficiency, but if the ratio gets too high, the collaboration efficiency will be exacerbated because overall informational diversity is threatened and knowledge contribution of less motivated participants is intimidated. Cox regression models were formulated for each of the focal variables-Pareto ratio and Gini coefficient-with seven control variables such as the number of editors involved in an article, the average time length between successive edits of an article, the number of sections a featured article has, etc. The dependent variable of the Cox models is the time spent from article initiation to promotion to the featured article level, indicating the efficiency of knowledge collaboration. To examine whether the effects of the focal variables vary depending on the characteristics of a group task, we classified 2,978 featured articles into two categories: Academic and Non-academic. Academic articles refer to at least one paper published at an SCI, SSCI, A&HCI, or SCIE journal. We assumed that academic articles are more complex, entail more information processing and problem solving, and thus require more skill variety and expertise. The analysis results indicate the followings; First, Pareto ratio and inequality of knowledge sharing relates in a curvilinear fashion to the collaboration efficiency in an online community, promoting it to an optimal point and undermining it thereafter. Second, the curvilinear effect of Pareto ratio and inequality of knowledge sharing on the collaboration efficiency is more sensitive with a more academic task in an online community.

• Journal of Global Scholars of Marketing Science
• /
• v.17 no.4
• /
• pp.51-89
• /
• 2007

INTRODUCTION Due to the high broadband internet penetration rate and its group-oriented culture, various types of online communities operate in Korea. This study use 'Uses and Gratification Approach, and argue that members' usage-needs satisfaction with brand community is an important factor for promoting community commitment. Based on previous studies identifying the effect of brand image on consumers' responses to various marketing stimuli, this study hypothesizes that brand image can be a moderate variable affecting the relationship between usage-needs satisfaction with brand community and members' commitment to brand community. This study analyzes the influence of usage-needs satisfaction on brand community commitment and how apparel brand image affects the relationships between usage-needs satisfactions and community commitments. The hypotheses of this study are proposed as follows. H1-3: The usage-needs satisfaction of apparel brand community (interest, transaction, relationship needs) influences emotional (H1), continuous (H2), and normative (H3) commitments to apparel brand communities. H4-6: Apparel brand image has a moderating effect on the relationship between usage-needs satisfaction and emotional (H4), continuous (H5), and normative (H6) commitments to apparel brand communities. METHODS Brand communities founded by non-company affiliates were excluded and emphasis was placed instead on communities created by apparel brand companies. Among casual apparel brands registered in 6 Korean portal sites in August 2003, a total of 9 casual apparel brand online communities were chosen, depending on the level of community activity and apparel brand image. Data from 317 community members were analyzed by exploratory factor analysis, moderated regression analysis, ANOVA, and scheffe test. Among 317 respondents answered an online html-type questionnaire, 80.5% were between 16 to 25 years old. There were a total of 150 respondents from apparel brand communities(n=3) recording higher-than-average brand image scores (Mean > 3.75) and a total of 162 respondents from apparel brand communities(n=6) recording lower-than-average brand image scores(Mean < 3.75). In this study, brand community commitment was measured by a 5-point Likert scale: emotional, continuous and normative commitment. The degree of usage-needs satisfaction (interest, transaction, relationship needs) was measured on a 5-point Likert scale. The level of brand image was measured by a 5-point Likert scale: strength, favorability, and uniqueness of brand associations. RESULTS In the results of exploratory factor analysis, the three usage-needs satisfactions with brand community were classified as interest, transaction, and relationship needs. Brand community commitment was also divided into the multi-dimensional factors: emotional, continuous, and normative commitments. The regression analysis (using a stepwise method) was used to test the influence of 3 independent variables (interest-needs satisfaction, transaction-needs, and relationship-needs satisfactions) on the 3 dependent variables (emotional, continuous and normative commitments). The three types of usage-needs satisfactions are positively associated with the three types of commitments to apparel brand communities. Therefore, hypothesis 1, 2, and 3 were significantly supported. Moderating effects of apparel brand image on the relationship between usage-needs satisfaction and brand community commitments were tested by moderated regression analysis. The statistics result showed that the influence of transaction-needs on emotional commitment was significantly moderated by apparel brand image. In addition, apparel brand image had moderating effects on the relationship between relationship-needs satisfaction and emotional, continuous and normative commitments to apparel brand communities. However, there were not significant moderate effects of apparel brand image on the relationships between interest-needs satisfaction and 3 types of commitments (emotional, continuous and normative commitments) to apparel brand communities. In addition, the influences of transaction-needs satisfaction on 2 types of commitments (continuous and normative commitments) were not significantly moderated by apparel brand image. Therefore, hypothesis 4, 5 and 6 were partially supported. To explain the moderating effects of apparel brand image, four cross-tabulated groups were made by averages of usage-needs satisfaction (interest-needs satisfaction avg. M=3.09, transaction-needs satisfaction avg. M=3.46, relationship-needs satisfaction M=1.62) and the average apparel brand image (M=3.75). The average scores of commitments in each classified group are presented in Tables and Figures. There were significant differences among four groups. As can be seen from the results of scheffe test on the tables, emotional commitment in community group with high brand image was higher than one in community group with low brand image when transaction-needs satisfaction was high. However, when transaction-needs satisfaction was low, there was not any difference between the community group with high brand image and community group with low brand image regarding emotional commitment to apparel brand communities. It means that emotional commitment didn't increase significantly without high satisfaction of transaction-needs, despite the high apparel brand image. In addition, when apparel brand image was low, increase in transaction-needs did not lead to the increase in emotional commitment. Therefore, the significant relationship between transaction-needs satisfaction and emotional commitment was found in only brand communities with high apparel brand image, and the moderating effect of apparel brand image on this relationship between two variables was found in the communities with high satisfaction of transaction-needs only. Statistics results showed that the level of emotional commitment is related to the satisfaction level of transaction-needs, while overall response is related to the level of apparel brand image. We also found that the role of apparel brand image as a moderating factor was limited by the level of transaction-needs satisfaction. In addition, relationship-needs satisfaction brought significant increase in emotional commitment in both community groups (high and low levels of brand image), and the effect of apparel brand image on emotional commitment was significant in both community groups (high and low levels of relationship-needs satisfaction). Especially, the effect of brand image was greater when the level of relationship-needs satisfaction was high. in contrast, increase in emotional commitment responding to increase in relationship-needs satisfaction was greater when apparel brand image is high. The significant influences of relationship-needs satisfaction on community commitments (continuous and normative commitments) were found regardless of apparel brand image(in both community groups with low and high brand image). However, the effects of apparel brand image on continuous and normative commitments were found in only community group with high satisfaction level of relationship-needs. In the case of communities with low satisfaction levels of relationship needs, apparel brand image marginally increases continuous and normative commitments. Therefore, we could not find the moderating effect of apparel brand image on the relationship between relationship-needs satisfaction and continuous and normative commitments in community groups with low satisfaction levels of relationship needs, CONCLUSIONS AND IMPLICATIONS From the results of this study, we draw several conclusions; First, the increases in usage-needs satisfactions through apparel brand communities result in the increases in commitments to apparel brand communities, wheres the degrees of such relationship depends on the level of apparel brand image. That is, apparel brand image is a moderating factor strengthening the relationship between usage-needs satisfaction and commitment to apparel brand communities. In addition, the effect of apparel brand image differs, depending on the level and types of community usage-needs satisfactions. Therefore, marketers of apparel brand companies must determine the appropriate usage-needs, depending on the type of commitment they wish to increase and the level of their apparel brand image, to promote member's commitments to apparel brand communities. Especially, relationship-needs satisfaction was very important factor for increasing emotional, continuous and normative commitments to communities. However the level of relationship-needs satisfaction was lower than interest-needs and transaction-needs. satisfaction. According to previous study on apparel brand communities, relationship-need satisfaction was strongly related to member's intention of participation in their communities. Therefore, marketers need to develope various strategies in order to increase the relationship- needs as well as interest and transaction needs. In addition, despite continuous commitment was higher than emotional and normative commitments, all types of commitments to apparel brand communities had scores lower than 3.0 that was mid point in 5-point scale. A Korean study reported that the level of members' commitment to apparel brand community influenced customers' identification with a brand and brand purchasing behavior. Therefore, marketers should try to increase members' usage-needs satisfaction and apparel brand image as the necessary conditions for bringing about community commitments. Second, marketers should understand that they should keep in mind that increasing the level of community usage needs (transaction and relationship) is most effective in raising commitment when the level of apparel brand image is high, and that increasing usage needs (transaction needs) satisfaction in communities with low brand image might not be as effective as anticipated. Therefore, apparel companies with desirable brand image such as luxury designer goods firms need to create formal online brand communities (as opposed to informal communities with rudimentary online contents) to satisfy transaction and relationship needs systematically. It will create brand equity through consumers' increased emotional, continuous and normative commitments. Even though apparel brand is very famous, emotional commitment to apparel brand communities cannot be easily increased without transaction-needs satisfaction. Therefore famous fashion brand companies should focus on developing various marketing strategies to increase transaction-needs satisfaction.