Purpose The purpose of this study was to examine the changing trends of swimsuit perception by using SNS big data. Methods By using “swimsuit” and “swimsuit brand” as key words, data was searched through blogs, cafes, Jisiksin(Tip), news, and web documents provided by naver and daum. This study used 2 years of data from January 1st, 2014 to December 31st, 2015 and social matrix program Textom was used for extracting matrix data and analyze them for frequency. To visualize data networking, NetDraw of UCINET6 program was used. Results Through analyzing the popular link words to the key words, it was known that the key words were 'swimsuit brand', 'children's swimsuit', 'rash guard', 'women's swimsuit', and 'model' in the order in 2014, and ‘swimsuit brand', 'rash guard', 'children's swimsuit', 'women's swimsuit', and 'Arena’ in the order in 2015. Second, the median of connectivity values showed that it was high in ‘swimsuit brand', 'women's swimsuit', 'children's swimsuit', 'rash guard', and 'Arena’ in the order in 2014, and ‘swimsuit brand', 'rash guard', 'women's swimsuit', 'children's swimsuit', and 'Arena’ in the order in 2015. Third, th results of CONCOR analysis demonstrated that ‘female customer’, ‘couple swimsuit’, 'rash guard', ‘brand’, 'children's swimsuit', and ‘fashion’ were grouped in 2014, and ‘brand’, ‘fashion’, 'rash guard', ‘purchase factor', and 'children's swimsuit' were grouped in 2015.
Purpose The purpose of this study is to introduce the basic concepts and procedures for topic modeling and to explain topic modeling to news articles about dementia-related physical activities. And it is also to discuss the possibility of using topic Modeling in the field of physical education. Methods In this study, the LDA algorithm of topic modeling is explained and the analysis procedure is summarized step by step by text preprocessing, text formatting, and topic number determination. The application cases were selected from 274 news articles about dementia-related physical activities reported in 13 major daily newspapers from 2000 to 2018. Results When the number of topics is 3, the Coherence Score figure is the highest. Topic 1 is about welfare services for dementia patients, Topic 2 is about prevention of dementia, and Topic 3 is about dementia research. The ratio by each subject is Topic 2 (46.0%), Topic 3 (33.2%) and Topic 1 (20.8%) in order of high ratio. Conclusion Topic modeling is an effective methodology to extract potential information excluding subjectivity of researchers. It is expected to be used when searching for information in massive texts in the field of physical education.
PURPOSE This study aimed to investigate user perceptions regarding the mobile healthcare application of public health centers by using big data. METHODS The study data included 1,089 users’ reviews (from September 27, 2016 to December 23, 2021), which were analyzed using Python, Textom, KrKwic, UCINET 6, and the Net-draw program. RESULTS First, the evaluation of the application showed a higher number of “Good” responses (677 times) compared to “Bad” (329 times) and “Normal” responses (83 times). Second, network structures related to “Good” were “Like,” “Health care,” “Help,” “A sense of purpose,” “Grateful,” “Diet management,” “Exercise management,” “Easy,” “Recommendation,” “Satisfaction,” “Diet,” “Useful,” and so on. Third, network structures related to “Bad” were “Execution error,” “Request improvement,” “Question,” “Slow speed,” “Interlocking error,” “Lack of food type,” “Login error,” “Inconvenience,” “Delete and reinstall,” “Update error,” “Irritation,” “Connection error,” “Problem occurred,” “Direct input request,” “Not available,” “Waste of stars,” “Lack of function,” “Not enough,” “Stuffy,” “Lack of exercise,” and so on. Fourth, as a result of structural equivalence analysis, four clusters appeared: cluster 1 (negative function), cluster 2 (negative emotion), cluster 3 (positive function), and cluster 4 (positive emotion). CONCLUSIONS It is necessary to respond quickly in order to reflect on the users’ reviews, and active efforts are required to improve the program quality so that users can use it conveniently.
