APPLYING KNOWLEDGE DISCOVERY IN DATABASES TECHNIQUE TO THE STUDENTS&rsquo; STRESS LEVEL DATASET: A PROCESS IN DESIGNING A CAMPUS STUDENTS&rsquo; STRESS MANAGEMENT PROGRAM

Roselle  M. Soriano,; Melidiossa  V. Pagudpud,; Jennifer  O. Serrano,

APPLYING KNOWLEDGE DISCOVERY IN DATABASES TECHNIQUE TO THE STUDENTS’ STRESS LEVEL DATASET: A PROCESS IN DESIGNING A CAMPUS STUDENTS’ STRESS MANAGEMENT PROGRAM

Melidiossa V. Pagudpud | Roselle M. Soriano | Jennifer O. Serrano

Abstract:

People throughout the world are stressed about the COVID-19 outbreak. Everyone, including young people and university students are suffering. Proper stress management is particularly challenging for students because they confront numerous challenges while adjusting to their new academic routines. This study used the Knowledge Discovery in Databases (KDD) approach to extract knowledge from a dataset of students' stress levels gathered at Quirino State University Cabarroguis Campus in the Province of Quirino. The students must be clustered in order to conceptualize and implement stress management programs for the students on the campus. The RapidMiner tool was used to examine the DensityBased Spatial Clustering of Applications with Noise (DBSCAN), K-Means, and KMedoid algorithms. The silhouette indices of the various clustering methods were examined, and the results revealed that the K-Means algorithm with k = 3 and a silhouette index of 0.399 is the best clustering strategy for grouping the students. The tolerable group (cluster 0) had 223 students, the positive group (cluster 1) had 222 students, and the toxic group had 44 students (cluster 2). The data mining approach used in this study is critical for extracting meaningful information from the dataset in order to better understand the students' stress levels, which serves as a solid foundation for developing a campus students' stress management program.