Anugrah, Muh Ilham and Fitriani, Yessy and Widiyanto, Max Teja Ajie Cipta (2025) ANALISIS SENTIMEN PENGGUNA TWITTER TERHADAP BANJIR DI JAKARTA MENGGUNAKAN METODE NAIVE BAYES. Diploma thesis, ITPLN.
202031137_MUH ILHAM ANUGRAH_REVISI_SKRIPSI_M.ILHAM Anugrah.pdf
Restricted to Registered users only
Download (3MB)
Abstract
Banjir merupakan salah satu bencana alam yang sering melanda wilayah Jakarta dan menimbulkan dampak signifikan bagi masyarakat. Media sosial, khususnya Twitter, menjadi wadah bagi masyarakat untuk menyampaikan opini, keluhan, maupun informasi terkait peristiwa banjir. Penelitian ini bertujuan untuk menganalisis sentimen pengguna Twitter terhadap banjir Jakarta tahun 2025 dengan menggunakan metode Naïve Bayes. Data dikumpulkan melalui teknik web scraping dengan total 1.125 tweet yang diperoleh dari Desember 2024 hingga Juli 2025. Proses pra pemrosesan dilakukan melalui beberapa tahap, yaitu case folding, stopword removal, tokenizing, filtering, dan stemming. Selanjutnya, data diberi label sentimen positif, negatif, dan netral menggunakan InSet Lexicon, kemudian dilakukan vektorisasi dengan metode TF-IDF. Model klasifikasi dibangun menggunakan algoritma Multinomial Naïve Bayes dan dievaluasi dengan confusion matrix yang menghasilkan metrik akurasi, presisi, dan recall. Hasil penelitian menunjukkan bahwa metode Naïve Bayes mampu mengklasifikasikan sentiment
Flooding is a natural disaster that frequently strikes the Jakarta area and has a significant impact on the community. Social media, especially Twitter, has become a platform for people to express opinions, complaints, and information related to flooding. This study aims to analyze Twitter user sentiment towards the 2025 Jakarta flood using the Naïve Bayes method. Data was collected through web scraping techniques with a total of 1,125 tweets obtained from December 2024 to July 2025. The pre-processing process was carried out through several stages, namely case folding, stopword removal, tokenizing, filtering, and stemming. Next, the data was labeled with positive, negative, and neutral sentiment using InSet Lexicon, then vectorized using the TF-IDF method. A classification model was built using the Multinomial Naïve Bayes algorithm and evaluated with a confusion matrix that produces accuracy, precision, and recall metrics. The results show that the Naïve Bayes method is capable of classifying sentiment.
| Item Type: | Thesis (Diploma) |
|---|---|
| Uncontrolled Keywords: | Analisis Sentimen, Naive Bayes, Twitter, Banjir Jakarta, TF-IDF, InSet Lexicon-Based Sentiment Analysis, Naive Bayes, Twitter, Jakarta Flooding, TF-IDF, InSet Lexicon Based |
| Subjects: | Skripsi Bidang Keilmuan > Teknik Informatika |
| Divisions: | Fakultas Telematika Energi > S1 Teknik Informatika |
| Depositing User: | Sudarman |
| Date Deposited: | 14 Oct 2025 04:26 |
| Last Modified: | 14 Oct 2025 04:26 |
| URI: | https://repository.itpln.ac.id/id/eprint/2251 |
