• Journal of dental hygiene science
• /
• v.18 no.6
• /
• pp.380-388
• /
• 2018

This research team extracted keywords from 953 papers published in the Journal of Dental Hygiene Science from 2001 to 2018 for keyword and centrality analyses using the Keyword Network Analysis method. Data were analyzed using Excel 2016 and NetMiner Version 4.4.1. By conducting a deeper analysis between keywords by overall keyword and time frame, we arrived at the following conclusions. For the 17 years considered for this study, the most frequently used words in a dental science paper were "Health," "Oral," "Hygiene," and "Hygienist." The words that form the center by connecting major words in the Journal of Dental Hygiene through the upper-degree centrality words were "Health," "Dental," "Oral," "Hygiene," and "Hygienist." The upper betweenness centrality words were "Dental," "Health," "Oral," "Hygiene," and "Student." Analysis results of the degree centrality words per period revealed "Health" (0.227), "Dental" (0.136), and "Hygiene" (0.136) for period 1; "Health" (0.242), "Dental" (0.177), and "Hygiene" (0.113) for period 2; "Health" (0.200), "Dental" (0.176), and "Oral" (0.082) for period 3; and "Dental" (0.235), "Health" (0.206), and "Oral" (0.147) for period 4. Analysis results of the betweenness centrality words per period revealed "Oral" (0.281) and "Health" (0.199) for period 1; "Dental" (0.205) and "Health" (0.169) for period 2, with the weight then dispersing to "Hygiene" (0.112), "Hygienist" (0.054), and "Oral" (0.053); "Health" (0.258) and "Dental" (0.246) for period 3; and "Oral" (0.364), "Health" (0.353), and "Dental" (0.333) for period 4. Based on the above results, we hope that further studies will be conducted in the future with diverse study subjects.

• Journal of Korean Academy of Nursing
• /
• v.47 no.6
• /
• pp.806-816
• /
• 2017

Purpose: As comprehensive nursing care service has gradually expanded, it has become necessary to explore the various opinions about it. The purpose of this study is to explore the large amount of text data regarding comprehensive nursing care service extracted from online news and social media by applying a semantic network analysis. Methods: The web pages of the Korean Nurses Association (KNA) News, major daily newspapers, and Twitter were crawled by searching the keyword 'comprehensive nursing care service' using Python. A morphological analysis was performed using KoNLPy. Nodes on a 'comprehensive nursing care service' cluster were selected, and frequency, edge weight, and degree centrality were calculated and visualized with Gephi for the semantic network. Results: A total of 536 news pages and 464 tweets were analyzed. In the KNA News and major daily newspapers, 'nursing workforce' and 'nursing service' were highly rated in frequency, edge weight, and degree centrality. On Twitter, the most frequent nodes were 'National Health Insurance Service' and 'comprehensive nursing care service hospital.' The nodes with the highest edge weight were 'national health insurance,' 'wards without caregiver presence,' and 'caregiving costs.' 'National Health Insurance Service' was highest in degree centrality. Conclusion: This study provides an example of how to use atypical big data for a nursing issue through semantic network analysis to explore diverse perspectives surrounding the nursing community through various media sources. Applying semantic network analysis to online big data to gather information regarding various nursing issues would help to explore opinions for formulating and implementing nursing policies.

• The Journal of Internal Korean Medicine
• /
• v.38 no.1
• /
• pp.10-19
• /
• 2017

Objective: This study reviewed experimental studies on the effects of Korean medical treatment for diabetes mellitus (DM). Method: We reviewed 24 studies about DM that had been published since 2013. We searched the Korean Institute of Oriental Medicine (KIOM) database with the keyword '당뇨', '消渴', 'Diabetes'. Results: 1. The studies used various Korean medicine treatments; 15 used single medicinal herbs, 6 used herbal complexes, and 2 used acupuncture. 2. The measurement parameters used in the studies included blood glucose, body weight, histochemical change, lipid parameters, and food/water intake. Anti-diabetic effects were demonstrated in most of the studies. 3. The experimental animals used were rats or mice. There were 15 type 1 diabetes models, 7 type 2 diabetes models, and one normal model. Among them, 13 cases of chemical diabetes induced by Streptozotosin (STZ, type 1 diabetes inducer) were the most common. Conclusion: Further articles on Korean medical treatment of DM should be studied.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.419-425
• /
• 2001

A method to detect lots of porno documents on the internet is presented in this parer. The proposed method applies fuzzy inference mechanism to the conventional information retrieval techniques. First, several example sites on porno arc provided by users and then candidate words representing for porno documents are extracted from theme documents. In this process, lexical analysis and stemming are performed. Then, several values such as tole term frequency(TF), the document frequency(DF), and the Heuristic Information(HI) Is computed for each candidate word. Finally, fuzzy inference is performed with the above three values to weight candidate words. The weights of candidate words arc used to determine whether a liven site is sexual or not. From experiments on small test collection, the proposed method was shown useful to detect the sexual sites automatically.

• Journal of Information Technology Services
• /
• v.18 no.4
• /
• pp.135-149
• /
• 2019

Recently, there are many researches for extracting meaningful information from large amount of text data. Among various applications to extract information from text, topic modeling which express latent topics as a group of keywords is mainly used. Topic modeling presents several topic keywords by term/topic weight and the quality of those keywords are usually evaluated through coherence which implies the similarity of those keywords. However, the topic quality evaluation method based only on the similarity of keywords has its limitations because it is difficult to describe the content of a topic accurately enough with just a set of similar words. In this research, therefore, we propose topic keywords reorganizing method to improve the identifiability of topics. To reorganize topic keywords, each document first needs to be labeled with one representative topic which can be extracted from traditional topic modeling. After that, classification rules for classifying each document into a corresponding label are generated, and new topic keywords are extracted based on the classification rules. To evaluated the performance our method, we performed an experiment on 1,000 news articles. From the experiment, we confirmed that the keywords extracted from our proposed method have better identifiability than traditional topic keywords.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.859-865
• /
• 2023

In a situation where service providers are increasingly focusing on content development due to the intense competition in the OTT market, interactive content that encourages active participation from viewers is garnering significant attention. In response to this trend, research on interactive content is being conducted more actively. This study aims to analyze interactive content through text mining techniques, with a specific focus on online unstructured data. The analysis includes deriving the characteristics of keywords according to their weight, examining the relationship between OTT platforms and interactive content, and tracking changes in the trends of interactive content based on objective data. To conduct this analysis, detailed techniques such as 'Word Cloud', 'Relationship Analysis', and 'Keyword Trend' are used, and the study also aims to derive meaningful implications from these analyses.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.5
• /
• pp.22-28
• /
• 2008

This paper aims to offer a solution based on semantic document classification to improve e-Government utilization and efficiency for people using their own information retrieval system and linguistic expression. Generally, semantic document classification method is an approach that classifies documents based on the diverse relationships between keywords in a document without fully describing hierarchial concepts between keywords. Our approach considers the deep meanings within the context of the document and radically enhances the information retrieval performance. Concept Weight Document Classification(CoWDC) method, which goes beyond using existing keyword and simple thesaurus/ontology methods by fully considering the concept hierarchy of various concepts is proposed, experimented, and evaluated. With the recognition that in order to verify the superiority of the semantic retrieval technology through test results of the CoWDC and efficiently integrate it into the e-Government, creation of a thesaurus, management of the operating system, expansion of the knowledge base and improvements in search service and accuracy at the national level were needed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.131-154
• /
• 2022

Recently, researches on unstructured data analysis have been actively conducted with the development of information and communication technology. In particular, topic modeling is a representative technique for discovering core topics from massive text data. In the early stages of topic modeling, most studies focused only on topic discovery. As the topic modeling field matured, studies on the change of the topic according to the change of time began to be carried out. Accordingly, interest in dynamic topic modeling that handle changes in keywords constituting the topic is also increasing. Dynamic topic modeling identifies major topics from the data of the initial period and manages the change and flow of topics in a way that utilizes topic information of the previous period to derive further topics in subsequent periods. However, it is very difficult to understand and interpret the results of dynamic topic modeling. The results of traditional dynamic topic modeling simply reveal changes in keywords and their rankings. However, this information is insufficient to represent how the meaning of the topic has changed. Therefore, in this study, we propose a method to visualize topics by period by reflecting the meaning of keywords in each topic. In addition, we propose a method that can intuitively interpret changes in topics and relationships between or among topics. The detailed method of visualizing topics by period is as follows. In the first step, dynamic topic modeling is implemented to derive the top keywords of each period and their weight from text data. In the second step, we derive vectors of top keywords of each topic from the pre-trained word embedding model. Then, we perform dimension reduction for the extracted vectors. Then, we formulate a semantic vector of each topic by calculating weight sum of keywords in each vector using topic weight of each keyword. In the third step, we visualize the semantic vector of each topic using matplotlib, and analyze the relationship between or among the topics based on the visualized result. The change of topic can be interpreted in the following manners. From the result of dynamic topic modeling, we identify rising top 5 keywords and descending top 5 keywords for each period to show the change of the topic. Existing many topic visualization studies usually visualize keywords of each topic, but our approach proposed in this study differs from previous studies in that it attempts to visualize each topic itself. To evaluate the practical applicability of the proposed methodology, we performed an experiment on 1,847 abstracts of artificial intelligence-related papers. The experiment was performed by dividing abstracts of artificial intelligence-related papers into three periods (2016-2017, 2018-2019, 2020-2021). We selected seven topics based on the consistency score, and utilized the pre-trained word embedding model of Word2vec trained with 'Wikipedia', an Internet encyclopedia. Based on the proposed methodology, we generated a semantic vector for each topic. Through this, by reflecting the meaning of keywords, we visualized and interpreted the themes by period. Through these experiments, we confirmed that the rising and descending of the topic weight of a keyword can be usefully used to interpret the semantic change of the corresponding topic and to grasp the relationship among topics. In this study, to overcome the limitations of dynamic topic modeling results, we used word embedding and dimension reduction techniques to visualize topics by era. The results of this study are meaningful in that they broadened the scope of topic understanding through the visualization of dynamic topic modeling results. In addition, the academic contribution can be acknowledged in that it laid the foundation for follow-up studies using various word embeddings and dimensionality reduction techniques to improve the performance of the proposed methodology.

• Journal of the Korea Convergence Society
• /
• v.12 no.6
• /
• pp.233-239
• /
• 2021

Recently, the COVID-19 virus has caused people to stay indoors longer without going out. As a result of this, people's activity decreased sharply, and their weight gained. So people became more interested in health. Home training can be an alternative method to solve this problem. Accordingly, To find out the trends of home training, we collected articles from December 1, 2019, to November 30, 2020, using the news provided by BIG KINDS, a news analysis system. We analyzed frequency analysis, relational analysis according to weighting, and related word analysis with the program using the algorithm developed by BIG KINDS. In conclusion, first, it was found that home training is led by technology and the emergence of artificial intelligence. Second, it can be assumed that people mainly do home training using content and video services related to mobile carriers. Third, people had a high preference for Pilates in the sports category. It can be seen that the number of patent applications increased as the demand for exercise products related to Pilates increased. In the next study, we expect that this study will be used as primary data for various big data studies by supplementing the research methodology and conducting various analyses.

• Journal of the Korean Society for information Management
• /
• v.29 no.4
• /
• pp.191-208
• /
• 2012

Two fundamental aspects of speech summary generation are the extraction of key speech content and the style of presentation of the extracted speech synopses. We first investigated whether acoustic features (speaking rate, pitch pattern, and intensity) are equally important and, if not, which one can be effectively modeled to compute the significance of segments for lecture summarization. As a result, we found that the intensity (that is, difference between max DB and min DB) is the most efficient factor for speech summarization. We evaluated the intensity-based method of using the difference between max-DB and min-DB by comparing it to the keyword-based method in terms of which method produces better speech summaries and of how similar weight values assigned to segments by two methods are. Then, we investigated the way to present speech summaries to the viewers. As such, for speech summarization, we suggested how to extract key segments from a speech video efficiently using acoustic features and then present the extracted segments to the viewers.