ZHAHIRAH, NAJWA (2026) ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI ROBLOX DI GOOGLE PLAY STORE MENGGUNAKAN METODE RANDOM FOREST. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (555kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (205kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (293kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (243kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (4MB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (136kB) |
|
|
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (190kB) |
|
|
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (334kB) |
Abstract
The rapid development of digital technology, particularly in gaming applications, has increased the need to evaluate service quality based on user feedback. One valuable source of information is user reviews available on the Google Play Store. This study aims to analyze the sentiment of Roblox user reviews using the Random Forest algorithm. The dataset consisted of 6,545 Roblox user reviews collected from the Google Play Store through a web scraping technique. The collected data then underwent a text preprocessing stage to reduce noise in the text. Sentiment labeling was performed based on user ratings, where ratings of 4–5 were categorized as positive sentiment and ratings of 1–2 as negative sentiment. Furthermore, the text data were transformed into numerical representations using the Term Frequency–Inverse Document Frequency (TF�IDF) feature extraction method and divided into training and testing datasets with an 80:20 ratio. The classification process was carried out using the Random Forest algorithm, while the model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The experimental results indicate that the Random Forest model was able to classify the sentiment of Roblox user reviews effectively, achieving an accuracy of 85.40%, with precision, recall, and F1-score values indicating good classification performance. Overall, this study demonstrates that the Random Forest algorithm is effective for sentiment analysis of Indonesian�language application reviews. The findings also provide insights into users' perceptions of the quality of the Roblox application and are expected to serve as valuable input for developers in improving application quality, as well as a reference for future research in the field of sentiment analysis. Keywords: sentiment analysis, Google Play Store, Roblox, Random forest, Machine Learning. Perkembangan teknologi digital, terutama pada aplikasi permainan, menimbulkan kebutuhan untuk menilai kualitas layanan berdasarkan tanggapan pengguna. Salah satu sumber informasi yang dapat dimanfaatkan adalah ulasan pengguna pada Google Play Store. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi Roblox menggunakan metode Random Forest. Data yang digunakan terdiri atas 6.545 ulasan pengguna Roblox yang dikumpulkan dari Google Play Store menggunakan metode web scraping. Data yang terkumpul kemudian melalui tahapan text preprocessing untuk mengurangi noise pada teks. Pelabelan sentimen dilakukan berdasarkan rating ulasan, yaitu rating 4–5 sebagai sentimen positif dan rating 1–2 sebagai sentimen negatif. Selanjutnya, data teks diubah ke dalam bentuk numerik menggunakan proses ekstraksi fitur metode Term Frequency–Inverse Document Frequency (TF-IDF) dan dibagi menjadi data latih dan data uji dengan proporsi 80:20. Proses klasifikasi dilakukan menggunakan algoritma Random Forest, sedangkan evaluasi kinerja model dilakukan menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model Random Forest mampu mengklasifikasikan sentimen ulasan pengguna aplikasi Roblox dengan baik, memperoleh nilai akurasi sebesar 85,40% serta nilai precision, recall, dan F1-score yang menunjukkan performa klasifikasi yang baik. Secara keseluruhan, penelitian ini menunjukkan bahwa algoritma Random Forest efektif digunakan dalam analisis sentimen ulasan aplikasi berbahasa Indonesia. Hasil penelitian juga memberikan gambaran mengenai persepsi pengguna terhadap kualitas aplikasi Roblox sehingga dapat menjadi masukan bagi pengembang dalam meningkatkan kualitas layanan serta referensi bagi penelitian selanjutnya. Kata kunci: analisis sentimen, Google Play Store, Roblox, Random forest, Machine Learning
Actions (login required)
 |
View Item |
