Implementation of Sentiment Analysis for Student Academic Services Using Support Vector Machine and Long Short Term Memory (LSTM) Methods

I. Gusti Ngurah Bagus Caturbawa, Sri Asri, I. Wayan Suasnawa, Ni Gusti Ayu Putu Harry Saptarini, Kadek Yasa

2022

Abstract

Sentiment analysis on student satisfaction aims to obtain feedback related to quality assurance efforts, so that students’ opinions on perceived academic services can be known. This result is an evaluation for improving academic services at the Bali State Polytechnic. The method that can be used to find out the opinions of students having positive, negative or neutral perceptions is to use machine learning algorithms. In this study, two methods are used, namely Support Vector Machine and Long Short Term Memory. The results of this study indicate that student sentiment is classified into three classes positive, negative and neutral. The Support Vector Machine method obtained an accuracy rate of 0.81 (positive), 0.88 (negative) and 0.75 (neutral) while the Long Short Term Memory (LSTM) method obtained an accuracy of 0.91 (positive), 0.85 (negative) and 0.85 (neutral).

Paper Citation

in Harvard Style

Gusti Ngurah Bagus Caturbawa I., Asri S., Wayan Suasnawa I., Gusti Ayu Putu Harry Saptarini N. and Yasa K. (2022). Implementation of Sentiment Analysis for Student Academic Services Using Support Vector Machine and Long Short Term Memory (LSTM) Methods. In Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science - Volume 1: iCAST-ES; ISBN 978-989-758-619-4, SciTePress, pages 208-211. DOI: 10.5220/0011740100003575

in Bibtex Style

@conference{icast-es22,
author={I. Gusti Ngurah Bagus Caturbawa and Sri Asri and I. Wayan Suasnawa and Ni Gusti Ayu Putu Harry Saptarini and Kadek Yasa},
title={Implementation of Sentiment Analysis for Student Academic Services Using Support Vector Machine and Long Short Term Memory (LSTM) Methods},
booktitle={Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science - Volume 1: iCAST-ES},
year={2022},
pages={208-211},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011740100003575},
isbn={978-989-758-619-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science - Volume 1: iCAST-ES
TI - Implementation of Sentiment Analysis for Student Academic Services Using Support Vector Machine and Long Short Term Memory (LSTM) Methods
SN - 978-989-758-619-4
AU - Gusti Ngurah Bagus Caturbawa I.
AU - Asri S.
AU - Wayan Suasnawa I.
AU - Gusti Ayu Putu Harry Saptarini N.
AU - Yasa K.
PY - 2022
SP - 208
EP - 211
DO - 10.5220/0011740100003575
PB - SciTePress