• Journal of the Korean Society of Clothing and Textiles
• /
• v.36 no.10
• /
• pp.1015-1027
• /
• 2012

This study compares and analyzes cosmetics purchasing behavior according to the advertising and publicity implemented in women's monthly magazines as well as determines effective marketing strategies for the cosmetics industry. First, cosmetics advertising and publicity in women's monthly magazines can be classified into conventional advertising, advertorials, beauty news based on press releases, and beauty articles written by editors. In addition, consumer purchasing behavior has been examined in terms of use of information, purchasing intention, and purchasing experience. A study was conducted on women in their 20's to 40's in Seoul and Gyeonggi-do with 289 questionnaires used in the final analysis. Data were analyzed by common factor analysis, randomized block design, Bonferroni adjusted t-test, and multiple linear regression using SPSS 12.0/Windows. The results of the study can be summarized as follows. First, there was a difference in purchasing behavior according to types of cosmetics advertising and publicity in women's monthly magazines. Second, cosmetics shopping orientations were classified into six factors (the pursuit of impulsive purchasing and trends, well-known brands, convenience, low prices, efficacy and brand loyalty). There were significant effects of shopping orientation on cosmetics purchasing behavior according to the type of advertisement and publicity in women's monthly magazines.

• Journal of Korean Society for Quality Management
• /
• v.46 no.2
• /
• pp.225-242
• /
• 2018

Purpose: Recent trends have shown that the usage of big data analysis is becoming the core of identifying promising future technologies and emerging technologies. Accordingly, applying these trends by analyzing defense related data in such sources as journals, articles, and news will provide crucial clues in predicting and identifying core future technologies that can be used to develop creative and unprecedented future weapon systems that could change the warfare. Methods: To identify technology fields that are closely related to the 4th industrial revolution and recent technology development trends, environmental analysis, text mining, and military applicability survey have been included in the process. After the identification of core technologies that are militarily applicable, future weapon systems based on these technologies as well as their operation concepts are suggested. Results: Through the study, 73 important trends, from which 11 mega trends are derived, are identified. These mega trends can be expressed by 13 promising technology fields. From these technology fields, 248 promising future technologies are identified. Afterwards, further assessment is performed, which leads to the selection of 63 core technologies from the pool. These are named as "future defense technologies" which then become the bases for 40 future weapons systems that the military can use. Conclusion: Predicting future technologies using text mining analysis have been attempted by various organizations across the globe, especially in the fields related to the 4th industrial revolution. However, the application of it in the field of defense industry is unprecedented. Therefore, this study is meaningful in that it not only enables the military personnel to see promising future technologies that can be utilized for future weapon system development, but helps one to predict the future defense technologies using the method introduced in the paper.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.165-171
• /
• 2020

Most of the stock price prediction research using text mining uses news and SNS data. However, there is a weakness that it is difficult to get honest and vivid information about companies from them. This paper deals with the problem of the prediction for the direction of stock price by doing text mining the online company reviews of internal staff indicating employee satisfaction. The comparative analysis of the prediction models for the direction of stock price showed the prediction model, which adds internal employee reviews, has better performance than those that did not. This paper presents the convergence study using natural language processing in financial engineering. In the field of stock price prediction, This paper pursued a new methodology that used employee satisfaction. In practice, it is expected to provide useful information in the field of forecasting stock price direction.

• The Journal of the Korea Contents Association
• /
• v.18 no.9
• /
• pp.14-33
• /
• 2018

The purpose of this study to analyze the informatization trends in Korea through objective newspaper data for the period from 1998 to 2017 for informatization and library in four newspapers including KyoungHyang Newspaper, Kookmin Ilbo, Hankyoreh and Hankookilbo. Based on the analysis results of metadata and related words using BIGKinds, a news big data system, this study presented analysis of simple frequency, classification and classification of the keywords 'information', 'informatization' and 'library'. Based on the results, we compared and analyzed the tendency of informatization in the media through comparison with the 'Information White Paper' which is the publication of government agencies and with research about the research topic of 4 academic journals in the Library and Information Science field. This study tried to interpret the trends of informatization based on the media and it is meaningful that we analyzed the big data of newspaper article which is the long term and time series data. Based on the results of the study, implications of the growth and development of libraries with domestic informatization were suggested. It is expected that we will be able to create a basic framework for developing library informatization policy through the further studies.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.447-454
• /
• 2001

The automatic document classification is a method that assigns unlabeled documents to the existing classes. The automatic document classification can be applied to a classification of news group articles, a classification of web documents, showing more precise results of Information Retrieval using a learning of users. In this paper, we use the weighted Bayesian classifier that weights with keywords of a document to improve the classification accuracy. If the system cant classify a document properly because of the lack of the number of words as the feature of a document, it uses relevance word cluster to supplement the feature of a document. The clusters are made by the automatic word clustering from the corpus. As the result, the proposed system outperformed existing classification system in the classification accuracy on Korean documents.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.159-165
• /
• 2020

This study was attempted to identify the status of the work of the PA and provide the direction and evidence of policy making on the PA scheme. A convergence study was conducted to analyze a total of 23 articles of papers and Internet news through systematic review methodology. A literature search was performed using KISS, NDSL, RISS, National assembly library, and 11 major domestic daily newspapers and Youth Medical Newspaper. The analysis of eight papers showed that the PA's work-related exhaustion, job stress, unclear scope of work and lack of regulations reduced job satisfaction. Through 15 press articles, it was understood that it was urgent to establish a legal system and education system for qualifications and work as professional medical personnel amid a conflict of positive and negative opinions of related agencies. In order to increase the utilization of PA in the future, it is necessary to secure institutional devices suitable for Korean affairs and prepare educational programs.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.1-7
• /
• 2019

With the in-depth development of machine learning, the deep learning method has made great progress, especially with the Convolution Neural Network(CNN). Compared with traditional text sentiment classification methods, deep learning based CNNs have made great progress in text classification and processing of complex multi-label and multi-classification experiments. However, there are also problems with the neural network for text sentiment classification. In this paper, we propose a fusion model based on Long-Short Term Memory networks(LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.65-75
• /
• 2014

The main focus of this paper is to analyze trend of event informations in a variety of mass media by graphical visualization in axis of the time and location. Especially, continuity analysis based on user-generated social media can reflect the social impact of a certain event according to change time and location and their directional changes. To reveal the characteristics of continuous events, we survey the data set collected from news articles and tweets during two years. Based on case studies on 'disease' and 'leisure', we verify the effectiveness and usefulness of our proposed method. Even though some events occurred during same period, we showed directional changes which have high-impact in social media referred user interest's, compared with fact-based continuous visualization results.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.5
• /
• pp.27-34
• /
• 2020

Purpose: North Korea is a very close country geographically and culturally, but the nation has been one of the most secretive countries in the world. However, in recent years, North Korean society has been known to rapidly change its economic environment as well as its diplomatic and political environment. Since the gaining power of Jong-un, Kim in 2012, the North Korean government has implemented a new set of economic policies. North Korea has embraced limited market systems and mechanisms that have become a part of the formal planned economy. This study is concerned with the recent changes in the market and marketing activities of the communist country. It also seeks to gain an understanding of the changing market behavior of North Korean consumers. The purpose of this study is to enhance understanding of the market environments of North Korea and to provide appropriate implications for practitioners and researchers. Research design, data and methodology: Academic access to information that can understand North Korea's reality is minimal. Therefore, this study was conducted based on a qualitative analysis of secondary data. The existing literature on North Korea, related news and reports were the basis of the analysis. Analysis of secondary data related to North Korea was the main methodology of the study. Results: The official ideology of North Korea rejected most aspects of marketing, and yet there were marketing activities in North Korea. This article focuses on the development of market and marketing activities in North Korea during the recent years. This study indirectly confirmed that the market function is being activated in North Korea, and the basic functions of marketing such as advertisement, price, and distribution are being formed. In this process, the activation of the 'Jangmadang(market)' played a significant role. Conclusions: Research shows that North Korea is rapidly developing its own market function. In addition, marketing activities such as advertising and pricing strategies seem to be unprecedentedly active. However, due to changes in the political environment, the future development of North Korea's marketing is still in flux. Efforts to improve mutual understanding through continuous research are required.

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.366-375
• /
• 2013

Recently, management of Newspaper developmet of the internet news, broadcasting and free newspapers escalated competition between newspaper companies and other media companies as well as competition among newapaper companies. This paper analyzes the efficiency of Korean Newapaper using DEA model. We evaluate the CCR-O, BCC-O efficiency, SE and RTS of 30 Newspaper. We also suggest the Newpaper which can be benchmarked based on analyzed information. The result shows that ten Nespaper whose values of CCR-O efficiency are 1, and Fourteen Nespaper whose values of BCC efficiency are 1. RTS indicates IRS of 1 firms, DRS of 16 firms and CRS of 13 firms. To variables on the effectiveness of newspaper publishing companies for the understanding and performance analysis.