• Journal of Korea Multimedia Society
• /
• v.20 no.9
• /
• pp.1541-1550
• /
• 2017

The increasing number of multimedia content offered to the user demands content recommendation. In this paper, we propose a system for recommending content related to the content that user is watching. In the proposed system, relationship information between content is generated using relationship information between representative keywords of content. Relationship information between keywords is generated by analyzing keyword collocation frequencies in Internet news corpus. In order to handle big corpus data, we design an architecture that consists of a distributed search engine and a distributed data processing engine. Furthermore, we store relationship information between keywords and relationship information between keywords and content in NoSQL to handle big relationship data. Because the query optimizer of NoSQL is not as well developed as RDBMS, we propose query optimization techniques to efficiently process complex queries for recommendation. Experimental results show that the performance is improved by up to 69 times by using the proposed techniques, especially when the number of requested related keywords is small.

• Journal of Information Technology Services
• /
• v.11 no.1
• /
• pp.223-238
• /
• 2012

We have been provided with a plenty of information about IT through the conferences. However, it is hard to find enough information or the latest trends from conferences because there are too many conferences. In this situation, we analyzed the latest trends related to the field of IT by exploiting the Netminer which is one of the software for analysis of social networks and measuring the Cosine Similarity between conferences, based upon keywords which are included in the conferences. We analyzed keywords of 24 conferences related to the computer network part of the IEEE (Institute of Electrical and Electronics Engineers) in the case of foreign conferences. We also analyze keywords of the KIISE (Korean Institute of Information Scientists and Engineers) conferences in the case of domestic conferences, during 2009-2010. We identified the trends through the frequency of keywords, the change of top 10 keywords ranking and the similarity between conferences.

• Fashion & Textile Research Journal
• /
• v.25 no.6
• /
• pp.715-724
• /
• 2023

This study analyzed the shifts that occurred before and after the outbreak of COVID-19 by scrutinizing digital keywords derived from prominent culture media, such as books and instagram. The analysis identified trends rooted in digital terminology. For this study, the period 2017 to 2022 was divided into three-year segments, before and after the outbreak of COVID-19. Subsequently, an analysis was conducted using digital keywords to assess the number of digital-related books and book hashtags, the number of instagram mentions, and relevant keywords. We found that COVID-19 exerted a discernible influence on information related to digital keywords, substantially impacting both the book publishing market and instagram. Notably, digital-related books have been published in a variety of fields since the outbreak, and new fields are emerging. The year 2020 saw the most significant growth in the mentions of digital terms on instagram. Such terms were used in conjunction with terminology related to people working in a digital environment, endeavors aimed at revenue generation in online spaces, leisure activities associated with art and culture, and online service platforms. Through the analysis of digital keywords, this study is expected to contribute to the understanding of digital trends and their future trajectories.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.17-27
• /
• 2018

In this paper, the research trends of port hinterland from 1990 to 2018 were analyzed periodically using the Social Network Analysis (SNA) method. The data were collected from major academic journals and totally 116 papers were identified for analysis. The results of the analysis showed that in the first period (1990-1999), keywords can be listed as "containerization", "transport infrastructure" and developed countries related keywords like "Italy", "Canada" and "Germany". The results of the second period (2000-2009) were originated from keywords such as "regionalization", "competitiveness", "Asian consolidation" and "technology". In the third period (2010-2018), the results were derived from keywords such as "intermodal transport", "dry port", "container" and container related keywords and "shipping" and shipping related keywords. We could see the studies of port hinterland are becoming more systematic and integrated. This study provides some important implications for both academic, and industrial viewpoints, and it is helpful to understand the research concentration.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.2
• /
• pp.91-100
• /
• 2021

PURPOSE: This study analyzed the trends and characteristics of shoulder rehabilitation research through keyword analysis, and their relationships were modeled using text mining techniques. METHODS: Abstract data of 10,121 articles in which abstracts were registered on the MEDLINE of PubMed with 'shoulder' and 'rehabilitation' as keywords were collected using python. By analyzing the frequency of words, 10 keywords were selected in the order of the highest frequency. Word-embedding was performed using the word2vec technique to analyze the similarity of words. In addition, the groups were classified and analyzed based on the distance (cosine similarity) through the t-SNE technique. RESULTS: The number of studies related to shoulder rehabilitation is increasing year after year, keywords most frequently used in relation to shoulder rehabilitation studies are 'patient', 'pain', and 'treatment'. The word2vec results showed that the words were highly correlated with 12 keywords from studies related to shoulder rehabilitation. Furthermore, through t-SNE, the keywords of the studies were divided into 5 groups. CONCLUSION: This study was the first study to model the keywords and their relationships that make up the abstracts of research in the MEDLINE of Pub Med related to 'shoulder' and 'rehabilitation' using text-mining techniques. The results of this study will help increase the diversifying research topics of shoulder rehabilitation studies to be conducted in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.151-158
• /
• 2019

This study aimed to analyze the research trend related on obesity in physical education in Korea through the keyword network analysis and to establish a basic database for effective design of prospective studies. To achieve it the study crawled co-occured keywords with 'obesity' and 'physical education' from RISS and analyzed the list from 1990 to 2018. They include 25 journal papers and 38 dissertations. The results are as follows. First, recent 30 years 63 papers published in Korea with 'Obesity' and 'Physical Education', and there were 144 related keywords. Second, analyzing journals which have 'Obesity' and 'Physical Education', co-occured keywords in 4 centrality were 24 keywords(student, Korea, prevention, effect, level, body, activation, actual condition, lesson, child, investigation, participation, book, cause, activity, normal, degree, nutrition, physical strength, weight, elementary, light, inquiry, health), and 37 keyword occurred in top 30. Lastly, by CONCOR analysis the result could be divided into 2 clusters. One consists of the object of obesity and its invervention, and the other consists of negative keywords of obesity and its preliminery dimenstion. Through the result, this study showed the research trend which involves the concept of obesity in physical education in Korea. Through the result, prospective obesity research in physical education in Korea would be promoted.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.66-71
• /
• 2021

The purpose of this paper is to identify keywords related to museums, gamification, and visitors, and provide basic data that the museum market can be expanded by using gamification. That used to collect data for blogs, news, cafes, intellectuals, academic information by Naver and Daum which is Web documents in Korea, and Google Web, news, Facebook, Baidu, YouTube, and Twitter for analysis. For the data analysis period, a total of one year of data was selected from April 16, 2020 to April 16, 2021, after Corona. For data collection and analysis, the frequency and matrix of keywords were extracted through Textom, a social matrix site, and the relationship and connection centrality between keywords were analysed and visualized using the Netdraw function in the UCINET6 program. In addition, We performed CONCOR analysis to derive clusters for similar keywords. As a result, a total of 25,761 cases that analysing the keywords of museum, gamification and visitors were derived. This shows that the museum, gamification, and spectators are related to each other. Furthermore, if a system using gamification is developed for museums, the museum market can be developed.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.137-144
• /
• 2023

The purpose of this study is to examine consumers' perceptions of domestic infertility support policies based on infertility-related keywords and the trends of their changes. To this end, Momsholic, a mom cafe which has the most active infertility-related bulletin boards on Naver, was selected as the analysis target, and 'infertility' was selected as a keyword for data search. The data was collected for three months. In addition, network analysis and visualization were performed using R for data collection and analysis, and cross-validation was attempted using the NetDraw function of 'textom 1.0' and the UCINET6 program. As a result of the analysis, the main keywords were cost, artificial insemination, in vitro fertilization, freezing, harvest, ovulation, and how much. Next, looking at the central value of the degree of connection, it was found that the degree of connection between the words cost, cost, how much, problem, public health center, and artificial insemination was high. According to the results of this study, women who visit mom cafes due to infertility in Korea are more interested in the cost. It is believed to be closely related to infertility treatment as well as in vitro fertilization and egg freezing. Therefore, by examining keywords related toinfertility, it has academic significance in that it is possible to identify major factors that end users are interested in. Furthermore, it is possible to redefine the guidelines for domestic infertility support policies by presenting infertility support policies that reflect the factors of interest of end consumers.

• Journal of muscle and joint health
• /
• v.27 no.3
• /
• pp.255-267
• /
• 2020

Purpose: The purpose of this study is to compare topics through keywords related to nurses in internet portals and social media Pre coronavirus disease (COVID-19) era and during the COVID-19 era. Methods: For six months before and during the outbreak of COVID-19 in Korea, "nurse" was searched on the internet. For data collection, we implemented web crawlers in programming languages such as Python and collected keywords. The keywords collected were classified into three domains of topic Modeling. Results: The keyword 'nurse' increased by 15% during COVID-19 era. Keywords that ranked high in Term Frequency - Inverse Document Frequency (TF-IDF) values were before COVID-19, such as "nurse" and "C-section". during COVID-19, however, they were not only "nurse" but also "emergency" and "gown" related to pandemics. Conclusion: Various topics were being uploaded into the internet media. Nursing professionals should be interested in the text that is revealed in the internet media and try to continuously identify and improve problems.

• The Research Journal of the Costume Culture
• /
• v.27 no.4
• /
• pp.398-413
• /
• 2019

This study empirically analyzed the influence of fashion brands' marketing issues on actual sales and consumer preference-focusing on evaluation trends of brands over time by using the theoretical background and big data provided through literature. This study examined the influence of three fashion brands (Balenciaga, Vetements, and Off-White) that have recently seen a drastic increase in the number of searched volumes through social networks. To identify the consumer-brand evaluations and trends and the marketing issues, the time period was divided into Groups A and B, which are from 2014 to 2015 and from 2016 to 2017, respectively. This study analyzed the frequency of overlapping keywords by using the R program to graphically visualize the changes over the timeline. Specifically, this analysis extracted data mainly related to bags, wallets and accessories for 2014-2015, but in 2016-2017, all four brands saw a vast increase in the frequency of searching product keywords related to clothing and footwear, and newly extracted ones were the top keywords. When analyzing the big data with these keywords as indicators, I confirmed that the products related to bags, wallets, and accessories were shifted to those related to apparel and footwear. Consumers previously recognized luxury brands such as Balenciaga as accessories-oriented brands that were focused on handbags and sunglasses, but now they are gaining popularity and recognition among consumers as a fashion brand.