PERBANDINGAN METODE NAÏVE BAYES, SUPPORT VECTOR MACHINE(SVM) DAN LONG SHORT-TERM MEMORY(LSTM) UNTUK ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI SAYURBOX DI GOOGLE PLAY STORE

ARDELIA, EKA ABIDAH and Utami, Alvi Syahrini (2025) PERBANDINGAN METODE NAÏVE BAYES, SUPPORT VECTOR MACHINE(SVM) DAN LONG SHORT-TERM MEMORY(LSTM) UNTUK ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI SAYURBOX DI GOOGLE PLAY STORE. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021282126106_cover.pdf] Image
RAMA_55201_09021282126106_cover.pdf - Cover Image
Available under License Creative Commons Public Domain Dedication.
Download (181kB)
[thumbnail of RAMA_55201_09021282126106.pdf] Text
RAMA_55201_09021282126106.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (2MB)
[thumbnail of RAMA_55201_09021282126106_TURNITIN.pdf] Text
RAMA_55201_09021282126106_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (7MB)
[thumbnail of RAMA_55201_09021282126106_0022127804_01_front_ref.pdf] Text
RAMA_55201_09021282126106_0022127804_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.
Download (802kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_02.pdf] Text
RAMA_55201_09021282126106_0022127804_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (534kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_03.pdf] Text
RAMA_55201_09021282126106_0022127804_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (401kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_04.pdf] Text
RAMA_55201_09021282126106_0022127804_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (947kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_05.pdf] Text
RAMA_55201_09021282126106_0022127804_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (589kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_06.pdf] Text
RAMA_55201_09021282126106_0022127804_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (250kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_07_ref.pdf] Text
RAMA_55201_09021282126106_0022127804_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (227kB)
[thumbnail of RAMA_55201_09021282126106_0022127804_08_lamp.pdf] Text
RAMA_55201_09021282126106_0022127804_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.
Download (144kB)

Abstract

Sayurbox is an e-commerce application that provides fresh products directly from farmers to consumers. To understand user perception namely how users express their evaluations of the services and experiences when using the application this study conducts sentiment analysis on user reviews of Sayurbox from the Google Play Store using three classification algorithms: Naïve Bayes, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM). Feature extraction is performed using TF-IDF for Naïve Bayes and SVM, and pre-trained Word2Vec for LSTM. The dataset consists of thousands of user reviews written in Indonesian. Evaluation results show that the SVM model with a linear kernel and C=100 achieves the best accuracy at 91.42%, followed by LSTM with 85.92%, and Naïve Bayes with 81.63%. These findings indicate that SVM is the most effective method for classifying the sentiment of Sayurbox user reviews. Keywords: Sentiment Analysis, Naïve Bayes, Support Vector Machine, LSTM, TF-IDF, Word2Vec, Sayurbox.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Analisis Sentimen, Naive Bayes, Support Vector Machine, LSTM, TF-IDF, Word2Vec
Subjects: Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Eka Abidah Ardelia
Date Deposited: 09 Jul 2025 03:41
Last Modified: 09 Jul 2025 03:41
URI: http://repository.unsri.ac.id/id/eprint/177243

Actions (login required)

View Item View Item