Perbandingan Metode Support Vector Machine dan Random Forest dalam Menganalisis Pengaruh Musik Terhadap Penurunan Tingkat Stress Mahasiswi Semester 7 saat Skripsi (Studi Kasus : Universitas Darussalam Gontor)

Abstract

This research was conducted with the aim of measuring the reduction in stress levels among final semester female students at Darussalam Gontor University using the Support Vector Machine and Random Forest algorithms to classify the influence of music on the reduction of stress levels among 7th semester female students at Darussalam Gontor University while preparing their thesis. Using the CRISP-DM method, the data used were collected through a survey totaling three hundred forty-nine with ten attributes. The results of the classification show that the Random Forest algorithm is more capable of classifying the influence of music on the reduction of stress levels among seventh-semester female students at Darussalam Gontor University when writing their theses compared to the Support Vector Machine (SVM), with a 7:3 ratio for training and testing data, yielding an accuracy of 85% for Random Forest and 72% for Support Vector Machine. The data indicates that music, especially pop, has a significant effect in helping female students cope with stress. The Random Forest algorithm is considered a more appropriate method for analyzing this data because it has higher accuracy. This also inspires the use of music as therapy to reduce academic stress.