Skripsi

ANALISIS SENTIMEN ULASAN APLIKASI MYXL PADA GOOGLE PLAY STORE MENGGUNAKAN NAIVE BAYES

---

Penilaian

---

The growth of internet users in Indonesia, reaching 221 million in 2024, has significantly impacted the digital sector, including operator service applications such as myXL. This application facilitates user access to telecommunication services, yet discrepancies between user ratings and comments are often found. Therefore, sentiment analysis is needed to more accurately evaluate user satisfaction. This study aims to develop a sentiment analysis system for myXL app reviews using the naïve Bayes algorithm. The data consists of Indonesian-language reviews categorized into two classes, namely positive and negative. Naïve Bayes is chosen for its efficiency and capability to handle large, imbalanced datasets. The study also outlines the research methodology used to build the classification system. Results show that the naïve Bayes model achieves an average accuracy of 87%, precision of 88%, recall of 85%, and f-measure of 86%. In addition to consistent performance across folds, the model is effective in identifying user sentiment. In conclusion, naïve Bayes is a simple yet reliable approach for sentiment analysis in the Indonesian language context and can assist developers in understanding user needs automatically.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507005388	T182676	T1826762025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1826762025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xiii, 104 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.430 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Kecerdasan Buatan
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment