Skripsi

ANALISIS SENTIMEN PENGGUNA APLIKASI GAME ROBLOX PADA ULASAN GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA NAÏVE BAYES

---

The rapid advancement of information technology has significantly boosted the digital entertainment industry, notably the online gaming platform Roblox, which boasts over 111 million daily active users globally. In Indonesia, the high number of users correlates with a vast volume of reviews on the Google Play Store, encompassing diverse opinions on gameplay experience, technical issues, and application features. This study aims to conduct a sentiment analysis of Roblox user reviews by classifying opinions into positive and negative categories to provide insights for developers in enhancing service quality. This research employs a quantitative approach with text mining techniques. A total of 2,000 review data points were collected through web scraping using Python. The data preprocessing stages included cleaning, case folding, normalization, tokenizing, filtering, and stemming. Word weighting was performed using the Term Frequency-Inverse Document Frequency (TF-IDF) method. Sentiment classification was executed by applying the Naïve Bayes algorithm, with the dataset split into 80% training data and 20% testing data. The results indicate that the Naïve Bayes algorithm is capable of classifying user sentiment with performance measured via a confusion matrix. Based on the model testing, the study achieved an accuracy rate of 78%, a precision of 75%, a recall of 74%, and an F1-score of 75%. The analysis reveals that user sentiment is dominated by positive reviews, with primary complaints in negative reviews centered on system bugs and connection issues. This study demonstrates that the Naïve Bayes algorithm is effective in processing large volumes of game application review text automatically and accurately. Keywords: Sentiment Analysis, Roblox, Google Play Store, Naïve Bayes, TF-IDF.

---

Availability

Detail Information

Series Title

-

Call Number

T1942982026

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xxii, 299 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 6

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Informasi
Pembelajaran Mesin

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment