SAPUTRA, INDRA (2025) KLASIFIKASI DAN ANALISIS SENTIMEN OPINI PUBLIK TERHADAP HASIL GUGATAN ANIES BASWEDAN PADA PEMILIHAN PRESIDEN 2024 DI MAHKAMAH KONSTITUSI MENGGUNAKAN NAIVE BAYES, SVM, DAN KNN. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (606kB) | 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 (39kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (159kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (208kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (393kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (28kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (129kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (816kB) |
Abstract
This study aims to analyze public opinion regarding Anies Baswedan's lawsuit at the Constitutional Court in the 2024 Presidential Election using machine learningbased classification and sentiment analysis methods. The three algorithms used in this research are Naïve Bayes, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). The dataset was collected from the social media platform Twitter (X) and underwent preprocessing stages, including tokenization, stopword removal, stemming, and text transformation into numerical form using TF-IDF. The results indicate that Naïve Bayes achieved the highest accuracy in relevance classification (83%), outperforming SVM (82%) and KNN (76%), as well as in sentiment analysis with an accuracy of 68%, higher than KNN (63%) and SVM (59%). Sentiment analysis of relevant tweets revealed that public opinion was predominantly negative, reflecting dissatisfaction with the lawsuit outcome. These findings confirm that choosing the right algorithm and applying optimal preprocessing techniques can improve model accuracy and provide deeper insights into public opinion trends on social media. Keywords: Sentiment Analysis, Naïve Bayes, SVM, KNN, Public Opinion. Penelitian ini bertujuan untuk menganalisis opini publik terhadap hasil gugatan Anies Baswedan di Mahkamah Konstitusi pada Pemilihan Presiden 2024 menggunakan metode klasifikasi dan analisis sentimen berbasis machine learning. Tiga algoritma yang digunakan adalah Naïve Bayes, Support Vector Machine (SVM), dan K-Nearest Neighbors (KNN). Data diperoleh dari media sosial Twitter (X) dan telah melalui tahapan preprocessing, termasuk tokenisasi, penghapusan stopwords, stemming, dan transformasi teks ke bentuk numerik menggunakan TFIDF. Hasil penelitian menunjukkan bahwa Naïve Bayes memiliki akurasi terbaik dalam klasifikasi relevansi (83%) dibandingkan SVM (82%) dan KNN (76%), serta dalam analisis sentimen dengan akurasi 68%, lebih tinggi dibandingkan KNN (63%) dan SVM (59%). Dari analisis sentimen terhadap tweet yang relevan, ditemukan bahwa opini publik didominasi oleh sentimen negatif, yang mencerminkan ketidakpuasan terhadap hasil gugatan. Temuan ini menegaskan bahwa pemilihan algoritma yang tepat dan penerapan preprocessing yang optimal dapat meningkatkan akurasi model serta memberikan wawasan lebih mendalam mengenai tren opini publik di media sosial. Kata Kunci: Analisis Sentimen, Naïve Bayes, SVM, KNN, Opini Publik.
Actions (login required)
 |
View Item |
