Analisis Sentimen Respon Mahasiswa Terhadap Perkuliahan Daring Menggunakan Perbandingan Akurasi Algoritme Support Vector Machine Dan Decision Tree (Studi Kasus : It Telkom Purwokerto)

Nur, Tasya Tahir (2022) Analisis Sentimen Respon Mahasiswa Terhadap Perkuliahan Daring Menggunakan Perbandingan Akurasi Algoritme Support Vector Machine Dan Decision Tree (Studi Kasus : It Telkom Purwokerto). Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text COVER PERBAIKAN.pdf Download (757kB)
	Text ABSTRACT.pdf Download (35kB)
	Text ABSTRAK.pdf Download (37kB)
	Text BAB 1.pdf Download (43kB)
	Text BAB 2.pdf Download (254kB)
	Text BAB 3.pdf Download (77kB)
	Text BAB 4.pdf Restricted to Registered users only Download (535kB) | Request a copy
	Text BAB 5.pdf Download (36kB)
	Text DAFTAR PUSTAKA.pdf Download (156kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Lecture is an advanced process of formal learning from secondary education in the school education path at the tertiary level. Lectures are generally carried out directly (face to face) between lecturers and students, but due to the Corona Virus Disease pandemic or commonly abbreviated as Covid-19 since 2020, lectures have been conducted online (online) in accordance with a circular on preventing the spread of Corona Virus Disease (Covid). -19) in universities issued by the Ministry of Education and Culture (Kemdikbud). Some people certainly think this is a new thing, so there will be many opinions and views expressed by students (students) on this online learning. So it is necessary to conduct a sentiment analysis of the review of the online learning process. The purpose of the research is to compare algorithms to obtain the optimal algorithm in classifying student response sentiments to online lectures. The data used is sourced from student responses. The method used is the Support Vector Machine with a linear kernel and Decision Tree because the accuracy of the Support Vector Machine in measuring sentiment is always high and Decision Tree is a fairly popular method and the resulting data is more accurate. The 90:10 scenario produces an accuracy rate of 89% for the Support Vector Machine and 91% for the Decision Tree. In this study, it was concluded that the best algorithm was Decision Tree compared to Support Vector Machine in the sentiment analysis process of student responses to online lectures, case studies of the Telkom Purwokerto Institute of Technology. Keywords : Sentiment analysis, Decision Tree, Online Lecture, Support Vector Machine

Actions (login required)

View Item