VINATA, DHIFA RADINA (2026) ANALISIS SENTIMEN PENGGUNA GAME ROBLOX PADA MEDIA SOSIAL MENGGUNAKAN METODE SUPPORT VECTOR MACHINE. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
COVER.pdf Download (762kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
BAB 1.pdf Restricted to Registered users only Download (326kB) |
|
|
Text (BAB II)
BAB 2.pdf Restricted to Registered users only Download (475kB) |
|
|
Text (BAB III)
BAB 3.pdf Restricted to Registered users only Download (501kB) |
|
|
Text (BAB IV)
BAB 4.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB V)
BAB 5.pdf Restricted to Registered users only Download (273kB) |
|
|
Text (DAFTAR PUSTAKA)
DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (322kB) |
|
|
Text (LAMPIRAN)
LAMPIRAN.pdf Restricted to Registered users only Download (494kB) |
Abstract
Using the Support Vector Machine algorithm, this study aims to analyze users' perceptions of Roblox on the social media platforms Twitter and TikTok. The data used in this study were collected through a data scraping process using the keyword "Roblox" as the basis for data retrieval.The research stages included data preprocessing, sentiment labeling, feature extraction using the TF-IDF method, dataset splitting with an 80:20 ratio into training and testing data, model development using the SVM algorithm, and model performance evaluation.The preprocessing results indicated that a total of 6,149 data entries were deemed suitable and ready for further analysis. The sentiment labeling results showed that the Twitter dataset consisted of 1,558 positive sentiments and 317 negative sentiments, while the TikTok dataset contained 3,854 positive sentiments and 420 negative sentiments.After the data splitting process, a total of 5,725 data entries were used in the analysis, consisting of 1,846 data from Twitter and 3,879 data from TikTok. Based on the testing results, the SVM model achieved an accuracy of 95% on the Twitter dataset and 96% on the TikTok dataset.The findings indicate that the combination of the Support Vector Machine algorithm and the TF-IDF method demonstrates excellent performance in classifying users' sentiments toward Roblox on social media platforms. Keywords: Sentiment Analysis, Roblox, Social Media, TF-IDF, Support Vector Machine. Dengan menggunakan algoritma Support Vector Machine, penelitian ini bertujuan untuk menganalisis persepsi pengguna terhadap Roblox di media sosial Twitter dan TikTok. Data yang digunakan dalam penelitian ini dikumpulkan melalui proses scraping data dengan memanfaatkan kata kunci "Roblox" sebagai dasar pencarian. Tahapan penelitian mencakup proses preprocessing data, pelabelan sentimen, ekstraksi fitur menggunakan metode TF-IDF, pembagian dataset dengan rasio 80:20 ke dalam data latih dan data uji, penerapan algoritma SVM untuk pemodelan, serta evaluasi terhadap kinerja model. Hasil proses preprocessing menunjukkan bahwa sebanyak 6.149 data telah siap dan layak digunakan pada tahap analisis selanjutnya. Hasil pelabelan menunjukkan bahwa pada data Twitter terdapat 1.558 sentimen positif dan 317 sentimen negatif, sedangkan pada data TikTok terdapat 3.854 sentimen positif dan 420 sentimen negatif. Setelah dilakukan proses pembagian data, jumlah dataset yang digunakan sebanyak 5.725 data, yang terdiri atas 1.846 data dari Twitter dan 3.879 data dari TikTok. Berdasarkan hasil pengujian, model SVM memperoleh nilai akurasi sebesar 95% pada dataset Twitter dan 96% pada dataset TikTok. Hasil yang diperoleh menunjukkan bahwa kombinasi algoritma SVM dan metode TF-IDF mampu memberikan kinerja yang sangat baik dalam proses klasifikasi sentimen pengguna Roblox pada media sosial. Kata Kunci: Analisis Sentimen, Roblox, Sosial Media, TF-IDF, Support Vector Machine.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41822010083 |
| Uncontrolled Keywords: | Analisis Sentimen, Roblox, Sosial Media, TF-IDF, Support Vector Machine. |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.7 Multimedia Systems/Sistem-sistem Multimedia > 006.75 Social Multimedia/Multimedia Social 300 Social Science/Ilmu-ilmu Sosial > 300. Social Science/Ilmu-ilmu Sosial > 303 Social Process/Proses Sosial > 303.3 Coordination and Control/Koordinasi dan Kontrol > 303.38 Public Opinion/Opini Publik |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | khalimah |
| Date Deposited: | 11 Sep 2026 04:30 |
| Last Modified: | 11 Sep 2026 04:30 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/103786 |
Actions (login required)
 |
View Item |
