• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.285-302
• /
• 2013

This study identified topic shifts and patterns over time by analyzing an enormous amount of Twitter data whose characteristics are high accessibility and briefness. First, we extracted keywords for a certain product and used them for representing the topic network allows for intuitive understanding of keywords associated with topics by nodes and edges by co-word analysis. We conducted temporal analysis of term co-occurrence as well as topic modeling to examine the results of network analysis. In addition, the results of comparing topic shifts on Twitter with the corresponding retrieval results from newspapers confirm that Twitter makes immediate responses to news media and spreads the negative issues out quickly. Our findings may suggest that companies utilize the proposed technique to identify public's negative opinions as quickly as possible and to apply for the timely decision making and effective responses to their customers.

• Journal of Industrial Convergence
• /
• v.17 no.4
• /
• pp.33-38
• /
• 2019

Regional tourism is an effective means of revitalizing the local economy and improving the image of the region. In order to revitalize this, efforts should be made to create regionally specialized tourism products and to preserve the unique culture and traditions. Among them, gathering information about visitors and securing the quality competitiveness of the contents of tourism contents are very important to increase the potential of cultural tourism festival. This paper collects, refines, and processes the festival-related data in a specific area in order to enhance the visitor's tourism needs and satisfaction. In particular, negative words and positive words raised during the festival were analyzed through big data visualization using word cloud.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.39 no.2
• /
• pp.190-203
• /
• 2015

The fashion industry has been rearranged by Global SPA brands (like ZARA and H&M), which are powerful retailers that integrate the value chain ranging from manufacturing to sales. SPA brands can offer good quality of clothing at a reasonable price by cutting the margin between the supply chain. They are also called fast fashions since they make expedited efforts to respond to market trends and consumers. Despite the slow growth of the fashion industry in Korea, as global SPA brands rapidly expand market share, traditional fashion companies have launched several SPA brands such as MIXXO and SPAO (E-LAND), 8SECONDS (CHEIL INDUSTRIES). The few academic studies on this subject are focused on the analysis of secondary data such as news and books. The current research is qualitative and empirical attempts to explore the success factor of SPA brands with analysis of 1:1 in-depth interviews with experts who have worked for global SPAs such as Uniqlo, H&M, and ZARA, based on the grounded theory. The main phenomenon was shown to be that global SPA brands were popular since they offer a variety of products with a large assortment at reasonable and cheap prices in a large scale and multifunctional retail store. Most of them displayed main phenomena that can be realized due to the purchasing cycle of clothing that is shorter with consumers' regarding clothing as consumables. Global SPA brands had three types of marketing strategy: sellable product, sales strategy according to consumer response, and multifunctional stores. Each global SPA brand developed marketing strategies based on core competency and national conditions. The three success factors shorten the consumer decision making process of clothing. This study concludes with implications for practitioners of SPA brands born in Korea.

• Journal of Korea Game Society
• /
• v.18 no.5
• /
• pp.83-92
• /
• 2018

Many studies in deep learning show results as good as human's decision in various fields. And importance of activation of online-community and SNS grows up in game industry. Even it decides whether a game can be successful or not. The purpose of this study is to construct a system which can read texts and create comments according to schedule in online-community and SNS using deep learning. Using recurrent neural network, we constructed models generating a comment and a schedule of writing comments, and made program choosing a news title and uploading the comment at twitter in calculated time automatically. This study can be applied to activating an online game community, a Q&A service, etc.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.657-678
• /
• 2016

This study deals with the effect of online word-of-mouth (OWOM) variables on the box office. From the result of statistical analysis on 276 films with audiences of more than five hundred thousand released in the Korea from 2012 to 2015, it can be seen that the variables showing the size of OWOM (such as the number of the portal movie rater, blog, and news after release) are associated more with the box office than the portal movie rating showing the direction of OWOM as well as variables showing the inherent properties of the film such as grade, nationality, release month, release season, directors, actors, and distributors.

• Knowledge Management Research
• /
• v.20 no.3
• /
• pp.155-171
• /
• 2019

In the entertainment industry which has great uncertainty, it is essential to predict public preference first. Thanks to various mass media channels such as cable TV and internet-based streaming services, the reality audition program has been getting big attention every day and it is being used as a new window to new entertainers' debut. This phenomenon means that it is changing from a closed selection process to an open selection process, which delegates selection rights to the public. This is characterized by the popularity of the public being reflected in the selection process. Therefore, this study aims to implement a machine learning model which predicts the winner of , which has recently been popular in South Korea. By doing so, this study is to extend the research method in the cultural industry and to suggest practical implications. We collected the data of winners from the 1st, 2nd, and 3rd seasons of the Produce 101 and implemented the predictive model through the machine learning method with the accumulated data. We tried to develop the best predictive model that can predict winners of by using four machine learning methods such as Random Forest, Decision Tree, Support Vector Machine (SVM), and Neural Network. This study found that the audience voting and the amount of internet news articles on each participant were the main variables for predicting the winner and extended the discussion by analyzing the precision of prediction.

• Asia pacific journal of information systems
• /
• v.24 no.3
• /
• pp.325-344
• /
• 2014

Technical support of Window XP ended in March, 8, 2014, and it makes OS(Operating System) users fall in a state of confusion. Sudden decision making of OS upgrade and replacement is not a simple problem. Firms need to change the long term capacity plan in enterprise IS management, but they are pressed for time and cost to complete it. Individuals can not help selecting the second best plan, because the following OSs of Window XP are below expectations in performances, new PC sales as the opportunities of OS upgrade decrease, and the potential risk of OS technical support ending had not announced to OS users at the point of purchase. Microsoft as the OS vendors had not presented precaution or remedy for this confusion. Rather, Microsoft announced that the technical support of the other following OSs of Wndow XP such as Window 7 would ended in two years. This conflict between OS vendor and OS users could not happen in one time, but could recur in recent future. Although studies on the ways of OS user protection policy would be needed to escape from this conflict, few prior studies had conducted this issue. This study had challenge to cautiously investigate in such OS user's reactions as the confirmation with OS user's expectation in the point of purchase, three types of justice perception on the treatment of OS vendor, psychological contract violation, satisfaction and the other betrayal behavioral intention in the case of Window XP technical support ending. By adopting the justice perception on this research, and by empirically validating the impact on OS user's reactions, I could suggest the direction of establishing OS user protection policy of OS vendor. Based on the expectation-confirmation theory, the theory of justice, literatures about psychological contract violation, and studies about consumer betrayal behaviors in the perspective of Herzberg(1968)'s dual factor theory, I developed the research model and hypothesis. Expectation-confirmation theory explain that consumers had expectation on the performance of product in the point of sale, and they could satisfied with their purchase behaviors, when the expectation could have confirmed in the point of consumption. The theory of justice in social exchange argues that treatee could be willing to accept the treatment by treater when the three types of justice as distributive, procedural, and interactional justice could be established in treatment. Literatures about psychological contract violation in human behaviors explains that contracter in a side could have the implied contract (also called 'psychological contract') which the contracter in the other side would sincerely execute the contract, and that they are willing to do vengeance behaviors when their contract had unfairly been broken. When the psychological contract of consumers had been broken, consumers feel distrust with the vendors and are willing to decrease such beneficial attitude and behavior as satisfaction, loyalty and repurchase intention. At the same time, consumers feel betrayal and are willing to increase such retributive attitude and behavior as negative word-of-mouth, complain to the vendors, complain to the third parties for consumer protection. We conducted a scenario survey in order to validate our research model at March, 2013, when is the point of news released firstly and when is the point of one year before the acture Window XP technical support ending. We collected the valid data from 238 voluntary participants who are the OS users but had not yet exposed the news of Window OSs technical support ending schedule. The subject had been allocated into two groups and one of two groups had been exposed this news. The data had been analyzed by the MANOVA and PLS. MANOVA results indicate that the OSs technical support ending could significantly decrease all three types of justice perception. PLS results indicated that it could significantly increase psychological contract violation and that this increased psychological contract violation could significantly reduce the trust and increase the perceived betrayal. Then, it could significantly reduce satisfaction, loyalty, and repurchase intention, and it also could significantly increase negative word-of-month intention, complain to the vendor intention, and complain to the third party intention. All hypothesis had been significantly approved. Consequently, OS users feel that the OSs technical support ending is not natural value added service ending, but the violation of the core OS purchase contract, that it could be the posteriori prohibition of OS user's OS usage right, and that it could induce the psychological contract violation of OS users. This study would contributions to introduce the psychological contract violation of the OS users from the OSs technical support ending in IS field, to introduce three types of justice as the antecedents of psychological contract violation, and to empirically validate the impact of psychological contract violation both on the beneficial and retributive behavioral intentions of OS users. For practice, the results of this study could contribute to make more comprehensive OS user protection policy and consumer relationship management practices of OS vendor.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.33-56
• /
• 2016

Many researchers have focused on developing bankruptcy prediction models using modeling techniques, such as statistical methods including multiple discriminant analysis (MDA) and logit analysis or artificial intelligence techniques containing artificial neural networks (ANN), decision trees, and support vector machines (SVM), to secure enhanced performance. Most of the bankruptcy prediction models in academic studies have used financial ratios as main input variables. The bankruptcy of firms is associated with firm's financial states and the external economic situation. However, the inclusion of qualitative information, such as the economic atmosphere, has not been actively discussed despite the fact that exploiting only financial ratios has some drawbacks. Accounting information, such as financial ratios, is based on past data, and it is usually determined one year before bankruptcy. Thus, a time lag exists between the point of closing financial statements and the point of credit evaluation. In addition, financial ratios do not contain environmental factors, such as external economic situations. Therefore, using only financial ratios may be insufficient in constructing a bankruptcy prediction model, because they essentially reflect past corporate internal accounting information while neglecting recent information. Thus, qualitative information must be added to the conventional bankruptcy prediction model to supplement accounting information. Due to the lack of an analytic mechanism for obtaining and processing qualitative information from various information sources, previous studies have only used qualitative information. However, recently, big data analytics, such as text mining techniques, have been drawing much attention in academia and industry, with an increasing amount of unstructured text data available on the web. A few previous studies have sought to adopt big data analytics in business prediction modeling. Nevertheless, the use of qualitative information on the web for business prediction modeling is still deemed to be in the primary stage, restricted to limited applications, such as stock prediction and movie revenue prediction applications. Thus, it is necessary to apply big data analytics techniques, such as text mining, to various business prediction problems, including credit risk evaluation. Analytic methods are required for processing qualitative information represented in unstructured text form due to the complexity of managing and processing unstructured text data. This study proposes a bankruptcy prediction model for Korean small- and medium-sized construction firms using both quantitative information, such as financial ratios, and qualitative information acquired from economic news articles. The performance of the proposed method depends on how well information types are transformed from qualitative into quantitative information that is suitable for incorporating into the bankruptcy prediction model. We employ big data analytics techniques, especially text mining, as a mechanism for processing qualitative information. The sentiment index is provided at the industry level by extracting from a large amount of text data to quantify the external economic atmosphere represented in the media. The proposed method involves keyword-based sentiment analysis using a domain-specific sentiment lexicon to extract sentiment from economic news articles. The generated sentiment lexicon is designed to represent sentiment for the construction business by considering the relationship between the occurring term and the actual situation with respect to the economic condition of the industry rather than the inherent semantics of the term. The experimental results proved that incorporating qualitative information based on big data analytics into the traditional bankruptcy prediction model based on accounting information is effective for enhancing the predictive performance. The sentiment variable extracted from economic news articles had an impact on corporate bankruptcy. In particular, a negative sentiment variable improved the accuracy of corporate bankruptcy prediction because the corporate bankruptcy of construction firms is sensitive to poor economic conditions. The bankruptcy prediction model using qualitative information based on big data analytics contributes to the field, in that it reflects not only relatively recent information but also environmental factors, such as external economic conditions.

• Korean journal of communication and information
• /
• v.78
• /
• pp.177-205
• /
• 2016

This study set out to investigate the reality of local press and changes to the occupational identity of reporters through the job mobility of reporters at local newspapers. The study examined what reasons the reporters had when they retired from one of three paper newspapers in Daejeon, where they moved to, and how their career mobility was. Some of them remained in the field of journalism including paper newspapers of the same kind and Internet newspapers, and others moved to various areas including politics, administration, academy, economy, and culture and art. The biggest number of them said they left their old paper newspapers because of poor wages and welfare benefits and absence of future visions. Their decision of leaving their old paper newspapers was also influenced by restructuring, restrictions to coverage and reporting, and great workload. Before the IMF foreign currency crisis in 1997, the press labor market was a typical internal labor market with the practitioners joining a newspaper in open recruitment and climbing up the promotion ladder from a common reporter through Deputy Head and Head of a department to Director of a bureau. The emergence of new media and the financial difficulties of newspaper corporations were currently making the internal labor market worse. Reporters made active use of social capital such as regionalism, alumni ties, and news beats rather than changing jobs by increasing their professionalism through self-development, thus causing side effects including the weakened supervision and criticism functions of local newspapers and damaging their occupational identity as reporters.

• Korean journal of communication and information
• /
• v.38
• /
• pp.211-244
• /
• 2007

Article 17 and 18 of the Korean Constitution respectively prescribe the violation of individual's right to privacy and the secrecy of wire communication. Meanwhile, Article 20 of the Criminal Code provides that an act which is conducted within the ambit of laws or pursuant to accepted business practices or which does not violate the social norms shall not be punishable. In 1999, the Constitutional Court held that media reports on public matters of public figures must be given strong constitutional protection, and treated differently from reports on private matters of private figures. In accordance with the decision, the Supreme Court has expanded the scope of constitutional guarantee of freedom of expression since 2002. This study analyzes the issue of media liability for publication of illegally intercepted wire communication by a third person. Particularly, it reviews Seoul High Court's ruling on 'X-file scandal' which disclosed intercepted wire communications between notable public figures regarding a slush fund for a presidential candidate. In the light of this analysis, the study concludes that the media reporting of the intercepted communication does not violate social norms of Article 20, and therefore it is entitled to a constitutional privilege.