빅데이터 분석을 적용한 운동, 심리 및 치료에 관한 주요 속성과 경향 도출
Derivation of Key Attributes and Trends in Exercise, Mentality and Therapy Using Big Data Analysis
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study aims to analyze the trends and key attributes of exercise, mentality and therapy using big data analysis. The significance of this research lies in identifying the core attributes, emerging trends, and future directions of exercise, mentality and therapy. The data collection spanned three years, from January 2022 to December 2024, focusing on unstructured text data sourced from Naver, Google, and Daum. The keyword combination used for data collection was "exercise + mentality + therapy." Textom, a big data collection and analysis tool, was employed to gather and preprocess the data. The collected data were analyzed using Textom and UCINET 6, applying frequency analysis and TF-IDF analysis for text mining, along with CONCOR analysis for social network analysis. The frequency and TF-IDF analyses identified the top 30 terms associated with exercise, mentality and therapy over the past three years. Additionally, the CONCOR analysis categorized these terms into four clusters: counseling and rehabilitation, mental healthcare, social support, and well-being. This study provides valuable insights into the key attributes and trends related to exercise, mentality and therapy, contributing to the field by offering strategic implications for future research and practical applications.
Abstract
This study aims to analyze the trends and key attributes of exercise, mentality and therapy using big data analysis. The significance of this research lies in identifying the core attributes, emerging trends, and future directions of exercise, mentality and therapy. The data collection spanned three years, from January 2022 to December 2024, focusing on unstructured text data sourced from Naver, Google, and Daum. The keyword combination used for data collection was "exercise + mentality + therapy." Textom, a big data collection and analysis tool, was employed to gather and preprocess the data. The collected data were analyzed using Textom and UCINET 6, applying frequency analysis and TF-IDF analysis for text mining, along with CONCOR analysis for social network analysis. The frequency and TF-IDF analyses identified the top 30 terms associated with exercise, mentality and therapy over the past three years. Additionally, the CONCOR analysis categorized these terms into four clusters: counseling and rehabilitation, mental healthcare, social support, and well-being. This study provides valuable insights into the key attributes and trends related to exercise, mentality and therapy, contributing to the field by offering strategic implications for future research and practical applications.