• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1045-1055
• /
• 2007

Latent topic models are statistical models which automatically captures salient patterns or correlation among features underlying a data collection in a probabilistic way. They are gaining an increased popularity as an effective tool in the application of automatic semantic feature extraction from text corpus, multimedia data analysis including image data, and bioinformatics. Among the important issues for the effectiveness in the application of latent topic models to the massive data set is the efficient learning of the model. The paper proposes an accelerated learning technique for PLSA model, one of the popular latent topic models, by an incremental EM algorithm instead of conventional EM algorithm. The incremental EM algorithm can be characterized by the employment of a series of partial E-steps that are performed on the corresponding subsets of the entire data collection, unlike in the conventional EM algorithm where one batch E-step is done for the whole data set. By the replacement of a single batch E-M step with a series of partial E-steps and M-steps, the inference result for the previous data subset can be directly reflected to the next inference process, which can enhance the learning speed for the entire data set. The algorithm is advantageous also in that it is guaranteed to converge to a local maximum solution and can be easily implemented just with slight modification of the existing algorithm based on the conventional EM. We present the basic application of the incremental EM algorithm to the learning of PLSA and empirically evaluate the acceleration performance with several possible data partitioning methods for the practical application. The experimental results on a real-world news data set show that the proposed approach can accomplish a meaningful enhancement of the convergence rate in the learning of latent topic model. Additionally, we present an interesting result which supports a possible synergistic effect of the combination of incremental EM algorithm with parallel computing.

• Journal of Korean society of Dental Hygiene
• /
• v.9 no.1
• /
• pp.59-71
• /
• 2009

Objectives : The purpose of this study is to devise a way of the dental hygienist to explore the articles of dental hygienist that were presented in the newspaper during the recent 3 years of Korea. Methods : This study is to examine dental hygienist articles with content analysis in the KINDS(Korean Integrated News Database System) of the Korean Press Foundation. Data were gathered from the printed newspaper of Korea over a period of 3 years - 1 March, 2005 to 30 March 2008. News reports, comments and letters to the editor were analysed, which revealed an image of dental hygienist that we would like to explore and debate. The obtained data from the frequency, percentage, chi-squared test between categories after inter-coder reliability test (reliability 0.96). Results : The articles of dental hygienist according to type of newspaper, 'local newspaper' showed higher frequency than 'metropolitan newspaper'. It mix '치과위생사'(42.3%), '치위생사'(49.4%), and '위생사'(3.9%) in use of name. The article pattern, 'news' 40.0%, 'information commentary' 18.3%, 'interview man' 15.8%, 'special news' 14.2% in metropolitan newspaper, then, 'news' 72.6%, 'information commentary' 23.2% in local newspaper (p<0.05). Most plenty of subject is 'administration system', and then 'celebration', 'publicity'. It showed 'seoul' was 'information commentary', 'country' was 'administration system', 'whole' was 'legal duty', 'unrelated area' was 'social living' in the topic of article according to newsbeat(p<0.05). Conclusions : These results suggest that it is necessary to publicity name, duty of dental hygienist in metropolitan newspaper officially.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.2
• /
• pp.85-101
• /
• 2021

This study aims to gain insight through understanding the Metaverse, which has recently become a hot topic. The study utilizes the methods of case study and News Bigdata Analysis Services. The Metaverse can be defined as a world with no separation between the virtual and real worlds. Currently, the Metaverse is dominated mainly by the MZ generation, but just like smartphones have quickly entered our lives, the Metaverse will soon, too, become a part of our lives. To follow up on this change, all companies, including global companies, are going after the Metaverse. Today, the Metaverse is successfully being used in all types of fields, including gaming, performing arts, business, etc., and its essential technologies include VR/AR/MR/XR and AI. This study intends to help understand the Metaverse through a case analysis of Zepeto, which has 200 million users worldwide. On Zepeto, users can decorate their own avatars, hang out with friends, go to art galleries and performances, and create and sell items. Of these users, 90% are from outside of South Korea, and 80% are teenagers. With most of the users being underage, many legal and social problems also follow. Nevertheless, who will be the first to conquer the new world of the Metaverse will continue to be a big issue. This study also analyzes domestic news articles about the Metaverse by utilizing the BigKinds system. Starting in 1996, the number of articles about the Metaverse each year remains single digit, until in 2020 when the number sharply rises to 86 news. As of June 2021, there are 1,663 articles on the Metaverse. This study suggests that the Metaverse should now be carefully examined and closely followed.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.5
• /
• pp.779-803
• /
• 2023

The growth of digital news media and the stock price index has resulted in economic fluctuations in the fashion industry. This study examines the impact of fashion industry news and macroeconomic changes on the Textile & Wearing Apparel KOSPI over the past five years. An auto-regressive integrated moving average exogenous time series model was conducted using the fashion industry stock market index, the news topic index, and macro-economic indicators. The results indicated the topics of "Cosmetic business expansion" and "Digital innovation" impacted the Textile & Wearing Apparel KOSPI after one week, and the topics of "Pop-up store," "Entry into the Chinese fashion market," and "Fashion week and trade show" affected it after two weeks. Moreover, the topics of "Cosmetic business expansion" and "Entry into the Chinese fashion market" were statistically significant in the macroeconomic environment. Regarding the effect relation of Textile & Wearing Apparel KOSPI, "Cosmetic business expansion," "Entry into the Chinese fashion market," and consumer price fluctuation showed negative effects, while the private consumption change rate, producer price fluctuation, and unemployment change rate had positive effects. This study analyzes the impact of media framing on fashion industry business cycles and provides practical insights into managing stock market risk for fashion companies.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.9-16
• /
• 2020

The purpose of this study is to understand the public needs for AI education actively promoted and supported by the current government. In doing so, 11 metropolitan news articles and Twitter posts regarding AI education that have been posted from January 1, 2018 to December 31, 2019 were collected. Then, word frequency analysis using TF(Term Frequency) method and LDA(Latent Dirichlet Allocation) method of topic modeling analysis were conducted. The topics of the news articles turn out to be a macroscopic policy support such as 'training female manpower in the AI field' and 'curriculum reform of university and K-12', whereas the topics of twitter delineate more detailed social perception on future society, such as future competencies and pedagogical methods, including 'coexistence with intelligent robots', 'coding education', and 'humane education competence development'. The findings are expected to be used to suggest the implications for the composition and management of AI curriculum as well as the basic framework of human resources development in the future industry.

• Journal of Industrial Convergence
• /
• v.20 no.6
• /
• pp.27-35
• /
• 2022

The purpose of this study is to analyze the metaverse-related issues in the news big data from an educational perspective, explore their characteristics, and provide implications for the educational applicability of the metaverse and future education. To this end, 41,366 cases of metaverse-related data searched on portal sites were collected, and weight values of all extracted keywords were calculated and ranked using TF-IDF, a representative term weight model, and then word cloud visualization analysis was performed. In addition, major topics were analyzed using topic modeling(LDA), a sophisticated probability-based text mining technique. As a result of the study, topics such as platform industry, future talent, and extension in technology were derived as core issues of the metaverse from an educational perspective. In addition, as a result of performing secondary data analysis under three key themes of technology, job, and education, it was found that metaverse has issues related to education platform innovation, future job innovation, and future competency innovation in future education. This study is meaningful in that it analyzes a vast amount of news big data in stages to draw issues from an education perspective and provide implications for future education.

• 한국노년학
• /
• v.41 no.3
• /
• pp.353-371
• /
• 2021

The purpose of this study is to provide clues to social welfare policy making by revealing discourse on social intervention and response based on big data on elderly living alone in the COVID-19 situation. Keyword analysis, network analysis, and topic analysis were utilized to explore the ways in which news media have portrayed challenges facing older individuals and the ways in which the central and local government as well as private organization have responded to them. Results are as follows. First, networks(degree, closeness, betweenness) were formed around region, delivery, society, support, and vulnerability, suggesting an increased demand for economic assistance and social support as well as stronger service delivery systems. Second, key topics derived included "establishing public delivery systems", "establishing local networks", "Managing care gap", "Establishing a private economic support system", and "Establishing service organization system". Based on the research results, discourse on the organic role of government, communities and the private sector has been presented, suggesting policy and practical implications by proposing a discussion on how to intervene for elderly living alone in disaster situations such as COVID-19.

• Korean Journal of Community Nutrition
• /
• v.22 no.3
• /
• pp.248-258
• /
• 2017

Objectives: The purpose of the study was to develop a series of education materials as a card news format to provide nutrition information for pregnant and lactating women. Methods: The materials were developed in seven steps. As a first step, the needs of pregnant and lactating women were assessed by reviewing scientific papers and existing education materials, and by interviewing a focus group. The second step was to construct main categories and the topics of information. In step 3, a draft of the contents in each topic was developed based on the scientific evidence. In step 4, a draft of card news was created by editors and designers by editing the text and embedding images in the card news. In step 5, the text, images and sequences were reviewed to improve readability by the members of the project team and nutrition experts. In step 6, parts of the text or images or the sequences of the card news were revised based on the reviews. In step 7, the card news were finalized and released online to the public. Results: A series of 26 card news for pregnant and lactating women were developed. The series covered five categories such as nutrition management, healthy food choices, food safety, favorites to avoid, nutrition management in special conditions for pregnant and lactating women. The satisfaction of 7 topics of the card news was evaluated by 140 pregnant women, and more than 70% of the women were satisfied with the materials. Conclusions: The card news format materials developed in this study are innovative nutrition education tools, and can be downloaded on the homepage of the Ministry of Food and Drug Safety. Those materials can be easily shared in social media by nutrition educators or by pregnant and lactating women to use.

• Journal of Korean Library and Information Science Society
• /
• v.50 no.4
• /
• pp.381-403
• /
• 2019

Information on newspaper articles were categorized into different topics, and each categories within different topics were developed into a faceted taxonomies model which was combined with fundamental facets. After suggesting the plan to construct such a model, the research of actual faceted taxonomies were conducted. Faceted taxonomies divide information on news articles into different topics(such as politics, economies and others) and combine fundamental facets with categories(for example, politics can be sub-classified into general politics, administration, legal system, and others) and sub-categories. Each sub-categories can be further subdivided. In taxanomies, categories can have hierarchical relationships. Categories-Facets, for example, can be utilized to combine "arts" with "people", "action", "event", "time", "place" and others. And Sub-category of the classification of "arts" such as "art," "music," "dance" form hierarchical relationships with "arts" and, in turn, can be used for browsing and further inferences. Furthermore, combining category and facets results in hierarchical structure in order of fundamental facets. As for the pilot vocabulary construction, faceted taxonomies of 145 words from news paper articles on the topic of "arts" were constructed using all construction elements covered in this study.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.227-230
• /
• 2015

For analyzing and prediction of economic trends, it is necessary to collect particular economic news and stock data. Typical Web crawler to analyze the page content, collects document and extracts URL automatically. On the other hand there are forms of crawler that can collect only document of a particular topic. In order to collect economic news on a particular Web site, we need to design a crawler which could directly analyze its structure and gather data from it. The wrapper-based web crawler design is required. In this paper, we design a crawler wrapper for Economic news analysis system based on big data and implemented to collect data. we collect the data which stock data, sales data from USA auto market since 2000 with wrapper-based crawler. USA and South Korea's economic news data are also collected by wrapper-based crawler. To determining the data update frequency on the site. And periodically updated. We remove duplicate data and build a structured data set for next analysis. Primary to remove the noise data, such as advertising and public relations, etc.