ANALISIS SENTIMEN ULASAN APLIKASI RUANGGURU PADA PLAYSTORE MENGGUNAKAN METODE NAIVE BAYES

Tuzzahra, Zabrina (2023) ANALISIS SENTIMEN ULASAN APLIKASI RUANGGURU PADA PLAYSTORE MENGGUNAKAN METODE NAIVE BAYES. Undergraduate thesis, UPN Vateran Jawa Timur.

[img]
Preview
Text (Cover)
18082010030-Cover-digabungkan.pdf

Download (1MB) | Preview
[img] Text (Bab 1)
18082010030-Bab 1.pdf
Restricted to Registered users only until 29 January 2025.

Download (98kB)
[img] Text (Bab 2)
18082010030-Bab 2.pdf
Restricted to Registered users only until 29 January 2025.

Download (192kB)
[img] Text (Bab 3)
18082010030-Bab 3.pdf
Restricted to Registered users only until 29 January 2025.

Download (241kB)
[img] Text (Bab 4)
18082010030-Bab 4.pdf
Restricted to Registered users only until 29 January 2025.

Download (2MB)
[img]
Preview
Text (Bab 5)
18082010030-Bab 5.pdf

Download (24kB) | Preview
[img]
Preview
Text (Daftar Pustaka)
18082010030-Daftar Pustaka.pdf

Download (148kB) | Preview
[img] Text (Lampiran)
18082010030-Lampiran.pdf
Restricted to Registered users only until 29 January 2025.

Download (935kB)

Abstract

Ruangguru is an application that is engaged in the field of Education in particular online learning. The majority of Ruangguru application users are students from elementary school to high school, of course, get a lot of comments given by the user, therefore a sentiment analysis is needed to see how big is the response rate of Ruangguru application users. To perform sentiment analysis the Ruangguru application requires a Naïve Bayes Classifier algorithm which This method is considered very effective to apply and has a fairly high accuracy value. In sentiment analysis the data used is 3061 data with two classes, namely class positive and negative. In this study, 5 scenario research scenarios were carried out, from the five models it is obtained the best model that has the best accuracy results, namely the scenario the third experiment is Naïve Bayes with Var Smoothing. In the third experimental scenario in get an accuracy value of 85.58%, F1 Score of 91.29%, Recall of 94.2%, and Precision of 85.56%. From this it can be seen that there are many ways that you can carried out to optimize the classification value and performance value.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorArifiyanti, Amalia Anjani0712089201amalia_anjani.fik@upnjatim.ac.id
Thesis advisorKartika, Dhian Satria Yudha0722058601dhian.satria@upnjatim.ac.id
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76.6 Computer Programming
Q Science > QA Mathematics > QA76.625 Internet Programming
Divisions: Faculty of Computer Science > Departemen of Information Systems
Depositing User: zabrina tuzzahra
Date Deposited: 30 Jan 2023 03:29
Last Modified: 30 Jan 2023 03:29
URI: http://repository.upnjatim.ac.id/id/eprint/11912

Actions (login required)

View Item View Item