GRACESILIA, ANGELY ARTINI (2025) ANALISIS SENTIMEN RESPONS EMOSIONAL MASYARAKAT TERHADAP PERINGATAN DARURAT MENGGUNAKAN NAIVE BAYES CLASSIFIER. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (491kB) | 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 (111kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (512kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (270kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (31kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (170kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (653kB) |
Abstract
This study analyzes the emotional responses of the public to emergency alerts on social media using the Naive Bayes Classifier algorithm. A total of 2,448 Twitter data samples were collected between August 16 and December 1, 2024, using keywords such as "Emergency Alert" and "Reject MK Decision." The analysis included data crawling, text preprocessing, sentiment labeling (positive, negative, neutral), and classification using Gaussian, Multinomial, and Bernoulli Naive Bayes algorithms. The results show sentiment distribution as follows 38.90% negative, 35.67% neutral, and 25.44% positive. The dominant emotions identified were anger (22.23%), followed by surprise (9.78%) and sadness (8.04%). The Gaussian Naive Bayes model achieved the highest accuracy, reaching 93.77% for sentiment testing and 100% for emotional response testing. The Multinomial Naive Bayes model achieved 81.48% for sentiment testing and 100% for emotional responses, while the Bernoulli Naive Bayes model achieved 60.77% and 52.50%, respectively. This study provides insights into public response patterns to national emergency issues, which can serve as a foundation for more effective crisis communication strategies. Keywords : Sentiment Analysis, Emotional Response, Emergency Warning, MPR Decree, Naive Bayes Classifier. Penelitian ini menganalisis respons emosional masyarakat terhadap peringatan darurat di media sosial menggunakan algoritma Naive Bayes Classifier. Sebanyak 2.448 data Twitter dikumpulkan dalam periode 16 Agustus 1 Desember 2024 dengan kata kunci seperti "Peringatan Darurat" dan "Tolak Keputusan MK". Analisis meliputi crawling data, preprocessing teks, pelabelan sentimen (positif, negatif, netral), dan klasifikasi menggunakan Gaussian, Multinomial, dan Bernoulli Naive Bayes. Hasil menunjukkan distribusi sentimen 38,90% negatif, 35,67% netral, dan 25,44% positif. Emosi dominan yang teridentifikasi adalah marah (22,23%), diikuti oleh terkejut (9,78%) dan sedih (8,04%). Model Gaussian Naive Bayes memberikan akurasi tertinggi, mencapai 93,77% pada data uji untuk sentimen dan 100% untuk respons emosional. Multinomial Naive Bayes memiliki akurasi uji 81,48% untuk sentimen dan 100% untuk respons emosional, sedangkan Bernoulli Naive Bayes mencapai 60,77% dan 52,50%. Penelitian ini memberikan wawasan tentang pola respons masyarakat terhadap isu darurat nasional yang dapat menjadi dasar strategi komunikasi krisis yang lebih efektif. Kata kunci: Analisis Sentimen, Ketetapan MPR, Naive Bayes Classifier, Respons Emosional, Peringatan Darurat.
Actions (login required)
 |
View Item |
