Implementasi Algoritma Support Vector Machine dalam Klasifikasi Deteksi Depresi dari Postingan pada Media Sosial

  • Kameliya Putri Prodi Informatika Universitas Udayana
  • Made Agung Raharja Universitas Udayana

Abstract

Mental health issues, such as depression, have significant impacts on individuals and society. Early identification and detection of these conditions are crucial steps in providing appropriate interventions and supporting better recovery. With the increasing use of social media, many people have started sharing their thoughts, feelings, and experiences online. Social media provides an abundant platform for users to express themselves and interact with others. Posts on social media often reflect individuals' emotional states. Therefore, analyzing the content of these posts can provide valuable insights for monitoring and early detection of depressive symptoms. Machine learning has been widely used for automated text mining and classification tasks. A classification method that can be used to classify social media posts into depression and normal classes is the support vector machine. Based on the testing results of the Support Vector Machine algorithm in classifying posts on social media, the highest accuracy value obtained was 95.5% using a parameter value of C equal to 0.25. The Precision, recall, and F-1 score values were 96%.


Keywords: Mental healt issues, Depresion, Support Vector Machine, Classification

Published
2023-11-03
How to Cite
PUTRI, Kameliya; RAHARJA, Made Agung. Implementasi Algoritma Support Vector Machine dalam Klasifikasi Deteksi Depresi dari Postingan pada Media Sosial. Jurnal Nasional Teknologi Informasi dan Aplikasnya, [S.l.], v. 2, n. 1, p. 193-202, nov. 2023. ISSN 3032-1948. Available at: <https://ojs.unud.ac.id/index.php/jnatia/article/view/102526>. Date accessed: 21 nov. 2024.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.