Pengembangan Aplikasi Klasifikasi Teks E-mail Keluhan Akademik Pelanggan Studi Kasus: Operasional Kalbis Institute

Abstract

This study aims to develop an application that can classify messages written by Kalbis students. The data used is a text message of student questions or complaints that have been sent to the Academic Operations and Finance through the Gmail service. The message data will be classified into Academic Operation and Finance classes. The data will be weighted based on the frequency of its occurrence in all messages using the Term Frequency – Inverse Document Frequency (TF-IDF) method. Then the weighted data will be classified using the Multinomial Naïve Bayes method. The Incremental Method is a method used to develop applications. The results obtained in this study are applications that are able to classify student messages with a model accuracy value of 86%, with each precision, recall and f1-score : 0.9, 0.83 and 0.84 in iteration one and application interface with objects in it that can be works fine in iteration two.