HOWIL, JUSTIN (2019) ANALISA SENTIMEN TWITTER PEMILU 2024 MENGGUNAKAN SUPPORT VECTOR MACHINE, VADER, DAN RECURRENT NEURAL NETWORK. S1 thesis, Universitas Mercu Buana Bekasi.
|
Text
41519210079 - Justin Howil - 01 Cover.pdf Download (367kB) | Preview |
|
|
Text
41519210079 - Justin Howil - 02 Abstrak.pdf Download (325kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text
41519210079 - Justin Howil - 03 Bab 1.pdf Restricted to Registered users only Download (78kB) |
|
|
Text
41519210079 - Justin Howil - 04 Bab 2.pdf Restricted to Registered users only Download (117kB) |
|
|
Text
41519210079 - Justin Howil - 05 Bab 3.pdf Restricted to Registered users only Download (562kB) |
|
|
Text
41519210079 - Justin Howil - 06 Bab 4.pdf Restricted to Registered users only Download (387kB) |
|
|
Text
41519210079 - Justin Howil - 07 Bab 5.pdf Restricted to Registered users only Download (32kB) |
|
|
Text
41519210079 - Justin Howil - 08 Daftar Pustaka.pdf Restricted to Registered users only Download (118kB) |
|
|
Text
41519210079 - Justin Howil - 09 Lampiran.pdf Restricted to Registered users only Download (1MB) |
Abstract
ABSTRAK Dekatnya pelaksanaan pemilihan umum 2024 menyebabkan meningkatnya komentar dan opini masyarakat mengenai pesta demokrasi ini di media sosial. Salah satu platform yang paling banyak digunakan adalah Twitter. Dengan memanfaatkan Twitter API, kita dapat mengumpulkan data opini masyarakat yang sangat berharga untuk melakukan analisis sentimen. Analisis sentimen bertujuan untuk mengekstraksi pendapat masyarakat terhadap pelaksanaan Pemilu 2024, baik itu positif atau negatif. Algoritma klasifikasi sentimen yang digunakan adalah Support Vector Machine dengan metode tambahan TF-IDF sebagai algoritma pembobotan, dan algoritma SMOTE untuk menyeimbangkan kelas. Proses penentuan sentimen dilakukan dengan menggunakan algoritma VADER dan Recurrent Neural Network. Setelah melakukan pengujian menggunakan aplikasi RapidMiner dengan dataset berjumlah 2809 data, diperoleh hasil akurasi klasifikasi SVM (VADER) dan SVM (RNN) secara berturut-turut adalah 82,77% dan 73,06%, dengan AUC (Area Under Curve) sebesar 0,986 dan 0,914. Kata Kunci: SVM, Recurrent Neural Network, VADER, RapidMiner, Pemilu. ABSTRACT The upcoming 2024 general elections are drawing near, and many people are expressing their comments and opinions about this democratic event through social media. One of the most widely used social media platforms is Twitter. By utilizing the Twitter API, valuable data can be collected to perform sentiment analysis on public opinions. Sentiment analysis aims to extract the sentiments of the public towards the 2024 elections, whether they are positive or negative. The sentiment classification algorithm used is Support Vector Machine with an additional TFIDF method for weighting and the SMOTE algorithm for class balancing. The sentiment labelling process is conducted using the VADER and Recurrent Neural Network algorithms. Through testing using the RapidMiner application with a dataset of 2809 records, the classification accuracy of SVM (VADER) and SVM (RNN) were found to be 82.77% and 73.06% respectively, with an AUC (Area Under Curve) of 0.986 and 0.914. Keywords: SVM, Recurrent Neural Network, VADER, RapidMiner, Election.
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO 19 001 |
| NIM/NIDN Creators: | 41519210079 |
| Uncontrolled Keywords: | SVM, Recurrent Neural Network, VADER, RapidMiner, Pemilu. |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | siti maisyaroh |
| Date Deposited: | 18 Dec 2023 06:37 |
| Last Modified: | 18 Dec 2023 06:37 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/84751 |
Actions (login required)
 |
View Item |
