NADIA, AQILAH ZAHRA (2026) STUDI KOMPARASI ALGORITMA MACHINE LEARNING UNTUK ANALISIS SENTIMEN TERHADAP KEBIJAKANKONTRASEPSI BEDAH PRIA DI MEDIA SOSIAL. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
COVER.pdf Download (462kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
BAB1.pdf Restricted to Registered users only Download (95kB) |
|
|
Text (BAB II)
BAB2.pdf Restricted to Registered users only Download (223kB) |
|
|
Text (BAB III)
BAB3.pdf Restricted to Registered users only Download (205kB) |
|
|
Text (BAB IV)
BAB4.pdf Restricted to Registered users only Download (511kB) |
|
|
Text (BAB V)
BAB5.pdf Restricted to Registered users only Download (29kB) |
|
|
Text (DAFTAR PUSTAKA)
DAFTARPUSTAKA.pdf Restricted to Registered users only Download (154kB) |
|
|
Text (LAMPIRAN)
LAMPIRAN.pdf Restricted to Registered users only Download (473kB) |
Abstract
Public policies regarding vasectomy as part of birth control programs often trigger various reactions in the community, especially on Twitter, a platform for real-time opinion expression. The purpose of this study is to analyze sentiment regarding public perception of vasectomy policies by comparing the effectiveness of two algorithms: Naïve Bayes and Support Vector Machine (SVM). Data for this study was collected through a crawling technique on the Twitter platform using keywords related to vasectomy policies. The research stages included comprehensive data preprocessing, including data cleaning, tokenizing, and stopword removal, to ensure the quality of the processed data. The data was then manually categorized into three sentiment labels: positive, negative, and neutral. The analysis was conducted by training both models to recognize linguistic patterns in each label, which were then tested using evaluation metrics such as accuracy, precision, recall, and f1-score. The results of this analysis are expected to not only provide an objective picture of public opinion trends towards reproductive health policies but also serve as an empirical basis for the government in developing more persuasive and targeted public communication plans. Keywords: Sentiment Analysis, Vasectomy, Naïve Bayes, Support Vector Machine, Twitter, TF-IDF, Multiclass Classification, Binary Classification Kebijakan publik mengenai vasektomi sebagai bagian dari program pengendalian kelahiran seringkali memicu berbagai reaksi di masyarakat, terutama di media sosial Twitter yang menjadi wadah ekspresi opini secara real-time. Tujuan penelitian ini adalah untuk menganalisis sentimen terhadap persepsi masyarakat mengenai kebijakan vasektomi dengan mengomparasikan efektivitas dari dua algoritma, yaitu Naïve Bayes dan Support Vector Machine (SVM). Data penelitian ini dikumpulkan melalui teknik crawling pada platform Twitter menggunakan kata kunci terkait kebijakan vasektomi. Tahapan penelitian meliputi praproses data yang komprehensif, mencakup cleaning data, tokenizing, dan stopword removal, guna memastikan kualitas dari data yang diolah. Data kemudian dikategorikan secara manual ke dalam tiga label sentimen: positif, negatif, dan netral. Analisis dilakukan dengan melatih kedua model untuk mengenali pola linguistik pada setiap label, yang kemudian diuji menggunakan metrik evaluasi berupa accuracy, precision, recall, dan f1-score. Hasil dari analisis ini diharapkan tidak hanya memberikan gambaran objektif mengenai kecenderungan opini publik terhadap kebijakan kesehatan reproduksi, tetapi juga berfungsi sebagai landasan empiris bagi pemerintah dalam mengembangkan rencana komunikasi publik yang lebih persuasif dan tepat sasaran. Kata kunci: Analisis Sentimen, Vasektomi, Naïve Bayes, Support Vector Machine, Twitter, TF-IDF, Klasifikasi Multikelas, Klasifikasi Biner
Actions (login required)
 |
View Item |
