PUTRA, BAGUS ARYA (2025) PERBANDINGAN ALGORITMA SVM, NAIVE BAYES, DAN KNN DALAM KLASIFIKASI SENTIMEN PUBLIK DI MEDIA SOSIAL X. S1 thesis, Universitas Mercu Buana.
|
Text (HAL COVER)
01 COVER.pdf Download (477kB) | 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 (97kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (244kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (148kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (739kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (24kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (148kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (552kB) |
Abstract
Social media platform X has become a crucial medium for the public to express opinions on national political issues. One prominent issue that has attracted public attention is the call for the impeachment of Vice President Gibran Rakabuming by the Retired TNI Forum. This phenomenon reflects the high level of public response to political dynamics, which can be further analyzed through sentiment analysis approaches. This study aims to classify public opinion sentiments on platform X regarding the impeachment issue using machine learning techniques. Data were collected by scraping user comments using relevant keywords, followed by preprocessing and labeling into three sentiment classes: positive, negative, and neutral. To achieve optimal classification performance, this study compares three algorithms: Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbors (KNN). The evaluation results show that SVM achieved the highest accuracy among the three, although Naive Bayes and KNN also demonstrated competitive performance in processing text data. This research is expected to provide an objective overview of public perception toward national political issues and support more informed public policy decisions. Kata kunci: Sentiment Classification, Impeachment, Support Vector Machine, Naive Bayes, K-Nearest Neighbors. Media sosial X telah menjadi sarana penting bagi masyarakat untuk mengekspresikan opini mengenai isu-isu politik nasional. Salah satu isu yang menjadi sorotan publik adalah desakan pemakzulan Wakil Presiden Gibran Rakabuming oleh Forum Purnawirawan TNI. Fenomena ini menunjukkan tingginya respons publik terhadap dinamika politik, yang dapat dianalisis lebih lanjut melalui pendekatan analisis sentimen. Penelitian ini bertujuan untuk mengklasifikasikan sentimen opini publik di media sosial X terkait isu pemakzulan Gibran Rakabuming menggunakan pendekatan machine learning. Data dikumpulkan melalui scraping komentar dari media sosial X menggunakan kata kunci relevan, kemudian dilakukan tahap preprocessing dan pelabelan data ke dalam tiga kelas: positif, negatif, dan netral. Untuk memperoleh hasil klasifikasi yang optimal, penelitian ini membandingkan performa tiga algoritma, yaitu Support Vector Machine (SVM), Naive Bayes, dan K-Nearest Neighbors (KNN). Hasil pengujian menunjukkan bahwa SVM memberikan akurasi terbaik dibandingkan dua algoritma lainnya, namun Naive Bayes dan KNN juga menunjukkan performa yang kompetitif dalam menangani data teks. Penelitian ini diharapkan dapat memberikan gambaran objektif mengenai persepsi masyarakat terhadap isu politik nasional serta mendukung pengambilan kebijakan publik yang lebih tepat.. Kata kunci: Klasifikasi Sentimen, Pemakzulan, Support Vector Machine, Naive Bayes, K-Nearest Neighbors.
Actions (login required)
 |
View Item |
