Klasifikasi Kategori Cerita Pendek Menggunakan Support Vector Machine

  • M Faisal Afandi Universitas Udayana
  • Ngurah Agus Sanjaya ER Universitas Udayana


Short stories are fascinating literary works to read because they present concise narratives that don't require readers to spend a lot of time to complete a story. Although the stories are short, determining the story category still requires careful reading to understand the content. However, it can become challenging when there is a large number of stories to be classified. Therefore, this research aims to develop a system that can automatically classify short story texts. The method used in this research is SVM (Support Vector Machine). The research is conducted to assist in automatically classifying short stories and create a system that bridges people to enjoying written works while enhancing literacy. The data used consists of short stories in the categories of romance, horror, and religion. The best-performing model is obtained through the training and validation process using new data. The results of testing the SVM method with a 70:30 data scenario, and hyperparameter C=10, gamma = 0.1 with kernel rbf or gamma = scale with kernel linear, yield an accuracy of 96% with a precision of 96.72%, recall of 96.36%, and an f1-score of 96.40%.

Keywords: Cerita Pendek, Teks Klasifikasi, TF-IDF, Support Vector Machine

How to Cite
AFANDI, M Faisal; ER, Ngurah Agus Sanjaya. Klasifikasi Kategori Cerita Pendek Menggunakan Support Vector Machine. Jurnal Nasional Teknologi Informasi dan Aplikasnya, [S.l.], v. 2, n. 1, p. 203-210, nov. 2023. ISSN 3032-1948. Available at: <https://ojs.unud.ac.id/index.php/jnatia/article/view/102456>. Date accessed: 18 apr. 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.