Visualization analysis of junior school students' pubertal timing and social adaptability using data mining...

Area of Science:

• Adolescent Mental Health
• Data Mining Applications
• Educational Psychology

Background:

• Pubertal timing and social adaptability are critical factors in adolescent mental health.
• Traditional analysis of these factors relies on simple scoring, limiting detailed insights.
• Existing methods fail to capture nuanced relationships and individual student profiles.

Purpose of the Study:

• To apply data mining techniques for a deeper analysis of pubertal timing and social adaptability in adolescents.
• To explore novel conclusions not achievable through traditional statistical methods.
• To enhance the understanding and classification of students for targeted educational interventions.

Main Methods:

• Association rule mining was employed to identify relationships between student attributes, pubertal timing, and social adaptability.
• Clustering algorithms were utilized for a fine-grained analysis of social adaptability, grouping similar students.
• Data visualization techniques were incorporated to improve the interpretability of findings.

Main Results:

• Association rule mining uncovered significant correlations between basic attributes, pubertal timing, and social adaptability levels.
• Clustering successfully segmented students into distinct groups based on social adaptability, offering detailed profiles.
• The data mining approach yielded novel insights into adolescent social adaptability that traditional methods could not provide.

Conclusions:

• Data mining offers a powerful and effective approach for studying complex adolescent traits like pubertal timing and social adaptability.
• The methods presented provide a novel perspective for educators to gain a more accurate and detailed understanding of students.
• This research guides the application of data mining in adolescent mental health education, improving student classification and support.