Big Data Analysis of Sports and Physical Activities among Korean Adolescents

Abstract

The Korean government (Ministry of Culture, Sports and Tourism, Ministry of Health and Welfare, and Ministry of Education) has framed policies and conducted many projects to encourage adolescents to be more physically active. Despite these efforts, the participation rate of physical activity in Korean adolescents keeps decreasing. Thus, the purpose of this study was to analyze the perception of sports and physical activity in Korean adolescents through big data analysis of the last 10 years and to provide research data and statistical direction with regard to sports and physical activity participation in Korean adolescents. For data collection, data from 1 January 2010 to 31 December 2019 were collected from Naver (NAVER Corp., Seongnam, Korea), Daum (Kakao Corp., Jeju, Korea), and Google (Alphabet Inc., Mountain View, CA, USA), which are the most widely used search engines in Korea, using TEXTOM 4.0 (The Imc Inc., Daegu, Korea), a big data collection and analysis solution. Keywords such as “adolescent + sports + physical activity” were used. TEXTOM 4.0 can generate various collection lists at once using keywords. Collected data were processed through text mining (frequency analysis, term frequency–inverse document frequency analysis) and social network analysis (SNA) (degree centrality, convergence of iterated correlations analysis) by using TEXTOM 4.0 and UCINET 6 social network analysis software (Analytic Technologies Corp., Lexington, KY, USA). A total of 9278 big data (10.36 MB) were analyzed. Frequency analysis of the top 50 terms through text mining showed exercise (872), mind (851), health (824), program (782), and burden (744) in a descending order. Term frequency–inverse document frequency analysis revealed exercise (2108.070), health (1961.843), program (1928.765), mind (1861.837), and burden (1722.687) in a descending order. SNA showed that the terms with the greatest degree of centrality were exercise (0.02857), program (0.02406), mind (0.02079), health (0.02062), and activity (0.01872) in a descending order. Convergence of the iterated correlations analysis indicated five clusters: exercise and health, child to adult, sociocultural development, therapy, and program. However, female gender, sports for all, stress, and wholesome did not have a high enough correlation to form one cluster. Thus, this study provides basic data and statistical direction to increase the rate of physical activity participation in Korean adolescents by drawing significant implications based on terms and clusters through bid data analysis.

Data Mining Algorithm for Physical Health Monitoring of Young Students Based on Big Data

“…According to the needs of structural health monitoring and the characteristics of monitoring data, Zhongdong Duan et al [ 22 ] proposed a data mining framework for structural health monitoring, including task definition, data warehouse construction, data preprocessing, data mining, and program evaluation. Sung-Yan Park et al analyzed the rate of physical activity participation in Korean adolescents by drawing significant implications based on terms and clusters through big data analysis [ 23 ]. These studies have explored the application of big data in structural health monitoring and have excellent application prospects.…”

Perceptions and Key Attributes of Exercise Among Korean Men and Women During the COVID-19 Pandemic: A Comparative Study Using Big Data Analysis

“…Text mining analysis is the process of discovering new knowledge from a large volume and variety of a selected set of digital text [36][37][38][39] by extracting relevant terms, calculating their frequency of use, and finding their meaning [40]. Consequently, we used text mining analysis using both frequency and TF-IDF analyses: Frequency analysis calculates the number of times a term appears in a given document, and the TF-IDF approach is used to weigh each term according to its uniqueness in a text document [41,42]. Thus, the TF-IDF value increases as the frequency of a word in a document increases, while the number of documents including the specific word decreases [41].…”

“…Consequently, we used text mining analysis using both frequency and TF-IDF analyses: Frequency analysis calculates the number of times a term appears in a given document, and the TF-IDF approach is used to weigh each term according to its uniqueness in a text document [41,42]. Thus, the TF-IDF value increases as the frequency of a word in a document increases, while the number of documents including the specific word decreases [41].…”

Network analysis based on big data in social media of Korean adolescents’ diet behaviors

“…Another study on physical activity and exercise in school-aged youth aimed to provide a solution by analyzing a large number of scientific articles using text mining [ 14 ]. A study has also been conducted to analyze Korean adolescents’ perceptions of sports and physical activities through big data analysis over the last 10 years, and provide research data and statistical direction with regard to their participation in such activities [ 15 ]. Under the premise that social media plays an important role in young people’s daily lives, a study describing a big data approach to social media has been presented.…”