Big data analysis of mental health intervention effects in student-athletes: based on data mining techniques and affective computing algorithms

Big data analysis of mental health intervention effects in student-athletes: based on data mining techniques and affective computing algorithms

연구 분야: Databases

학회: Multimedia Tools and Applications

Student-athletes suffer specific pressures and obstacles in regard to their studies and sports performance, making mental health concerns a major concern among this age group. Efforts to improve student athletes' mental health have been established in response to these concerns. The introduction of big data analytic tools, however, can make it easier to conduct the extensive study of massive datasets needed to determine the efficacy of these treatments. In this research, we employed big data analysis to look at how different factors affect student-athletes stress and mental health. The phrases student-athlete, stress, and mental health were included as keywords. We conducted a comprehensive review of scholarly articles available on Google Scholar, spanning the period from Jan 2010 to Dec 31, 2019. Utilizing TEXTOM 4.5, we systematically analyzed unstructured text data, and further employed UCINET 6 for social network analysis (SNA). The study looked at 3149 major databases. Two data mining analyses, “Term Frequency-Inverse Document Frequency (TF-IDF)” and frequency analysis of terms were used. In order to determine the degree of node-linking and locate clusters, the study of social networks made use of Convergence and Centrality of Iterated Correlation Analysis (CONCOR). Six clusters were found by the CONCOR analysis: mental activity, student, dream start, food, and physical and sports activity. Our findings highlight the significance of developing interventions for student-athletes that reduce stress and enhance mental health.