NURHASANAH, NABILA DIAN (2025) ANALISIS SENTIMEN OPINI PUBLIK TERHADAP GERAKAN PEMBOIKOTAN PRODUK F&B PRO-ISRAEL DI MEDIA SOSIAL X MENGGUNAKAN NAIVE BAYES. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (332kB) | 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 (105kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (139kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (128kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (348kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (91kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (101kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (619kB) |
Abstract
This study was conducted to determine Indonesian public sentiment towards the boycott movement of Food & Beverage (F&B) products considered to support Israel, using social media platform X (formerly known as Twitter) as a data source. A total of 3,696 tweets were collected from 2023 to October 2024 using a crawling technique. The data was then processed through several stages, starting from text preprocessing, sentiment labeling using the InSet dictionary, to the sentiment classification process using the Naïve Bayes algorithm. Sentiment in this study was categorized into three types: positive, negative, and neutral. The model was tested using three variations of training and test data splits: 80:20, 70:30, and 60:40. Based on the evaluation results, the 80:20 data split scenario provided the best results with 62.78% accuracy and the highest F1-score in the positive sentiment category. Although the model's accuracy level is not yet very high, the results of this study still provide a useful picture of public views on social issues and geopolitical conflicts, and demonstrate the ability of the Naïve Bayes algorithm in classifying text-based sentiment from social media. Keywords: Sentiment Analysis, Boycotting Israeli Products, X, Naive Bayes, and Public Opinion Penelitian ini dilakukan untuk mengetahui bagaimana sentimen masyarakat Indonesia terhadap gerakan boikot produk Food & Beverage (F&B) yang dianggap mendukung Israel, dengan memanfaatkan media sosial X (dulu dikenal sebagai Twitter) sebagai sumber data. Sebanyak 3.696 cuitan dikumpulkan dari tahun 2023 sampai Oktober 2024 menggunakan teknik crawling. Data tersebut kemudian diproses melalui beberapa tahap, mulai dari pembersihan teks (text preprocessing), pelabelan sentimen menggunakan kamus InSet, hingga proses klasifikasi sentimen menggunakan algoritma Naïve Bayes. Sentimen dalam penelitian ini dikategorikan menjadi tiga jenis, yaitu positif, negatif, dan netral. Model diuji menggunakan tiga variasi pembagian data latih dan uji, yaitu 80:20, 70:30, dan 60:40. Berdasarkan hasil evaluasi, skenario pembagian data 80:20 memberikan hasil paling baik dengan akurasi 62,78% dan nilai F1-score tertinggi pada kategori sentimen positif. Walaupun tingkat akurasi model belum terlalu tinggi, hasil penelitian ini tetap memberikan gambaran yang berguna tentang pandangan publik terhadap isu sosial dan konflik geopolitik, serta menunjukkan kemampuan algoritma Naïve Bayes dalam melakukan klasifikasi sentimen berbasis teks dari media sosial. Kata kunci: Analisis Sentimen, Boikot Produk Israel, X, Naive Bayes, dan Opini Publik
Actions (login required)
 |
View Item |
