PERBANDINGAN METODE RANDOM FOREST DAN LOGISTIC REGRESSION UNTUK ANALISIS SENTIMEN ULASAN APLIKASI TUMBUH KEMBANG ANAK DI PLAY STORE

ALFYANDO, MUHAMMAD (2024) PERBANDINGAN METODE RANDOM FOREST DAN LOGISTIC REGRESSION UNTUK ANALISIS SENTIMEN ULASAN APLIKASI TUMBUH KEMBANG ANAK DI PLAY STORE. Undergraduate thesis, UPN Veteran Jawa Timur.

[img]
Preview
Text (Cover)
19081010037-cover.pdf

Download (944kB) | Preview
[img]
Preview
Text (BAB 1)
19081010037-bab1.pdf

Download (125kB) | Preview
[img] Text (BAB 2)
19081010037-bab2.pdf
Restricted to Registered users only until 18 January 2026.

Download (468kB)
[img] Text (BAB 3)
19081010037-bab3.pdf
Restricted to Registered users only until 18 January 2026.

Download (581kB)
[img] Text (BAB 4)
19081010037-bab4.pdf
Restricted to Registered users only until 18 January 2026.

Download (1MB)
[img]
Preview
Text (BAB 5)
19081010037-bab5.pdf

Download (115kB) | Preview
[img]
Preview
Text (Daftar pustaka)
19081010037-daftarpustaka.pdf

Download (119kB) | Preview

Abstract

Early childhood has an important role in forming the basis of development, which involves aspects such as religious values, morals, socio-emotional, language, cognitive, and physical motor skills. The concept of learning through play is the main foundation of the educational approach in early childhood. Parents have the responsibility to understand the education of today's children and utilize technology as a tool. This research explores apps on child development, specifically "Tentang Anak", "PrimaKu", and "Teman Bumil". The focus of the research involves sentiment analysis of app user reviews using Random Forest and Logistic Regression methods, with the results showing the best performance on each app. The results noted that in the "Tentang Anak" the Logistic Regression method achieved the highest accuracy with a value of 94.34%, while in the "PrimaKu" the Logistic Regression method also achieved the best accuracy of 88.52%. For "Teman Bumil" the Random Forest and Logistic Regression methods achieved the highest accuracy of 86.94% and 84.47% respectively. Sentiment analysis of user reviews provides a better understanding of users needs and preferences towards child education apps, thereby improving the quality of services provided by the apps.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorANGGRAENY, FETTY TRINIDN0711028201fettyangraeny.if@upnjatim.ac.id
Thesis advisorSIHANANTO, ANDREAS NUGROHONIDN0012049005andreas.nugroho.jarkom@upnjatim.ac.id
Subjects: Q Science > QA Mathematics > QA76.6 Computer Programming
T Technology > T Technology (General)
Divisions: Faculty of Computer Science > Departemen of Informatics
Depositing User: Muhammad Alfyando
Date Deposited: 19 Jan 2024 02:40
Last Modified: 19 Jan 2024 02:40
URI: http://repository.upnjatim.ac.id/id/eprint/19871

Actions (login required)

View Item View Item