Reyhana, Zakya (2018) Analisis Sentimen Pendapat Masyarakat Terhadap Pembangunan Infrastruktur Kota Surabaya Melalui Twitter dengan Menggunakan Support Vector Machine dan Neural Network. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211650010010-Master_Thesis.pdf - Accepted Version Download (1MB) | Preview |
Abstract
Pembangunan infrastruktur Kota Surabaya tengah digiatkan dan dalam prosesnya, berdampak pada aktivitas masyarakat sehari-hari. Berimbas dari dampak, masyarakat kerap memberi komentar atau pendapat masing-masing melalui media apa saja, termasuk media sosial yaitu Twitter. Twitter adalah layanan jejaring sosial dan mikroblog yang memungkinkan penggunanya untuk mengirim dan membaca pesan berbasis teks hingga 140 karakter. Pendapat masyarakat tersebut merupakan informasi penting tentang reaksi mereka terhadap program kota yang dilakukan, maka penting untuk didata dan dianalisis. Penelitian yang dilakukan adalah analisis sentimen masyarakat dengan menggunakan metode Support Vector Machine dan Neural Network. Metode algoritma yang efektif untuk klasifikasi teks diantaranya adalah Support Vector Machine (SVM) dan Neural Network (NN). Ketepatan klasifikasi SVM sebesar 92,67%, sedangkan NN 80,00%. Untuk perbandingan, metode SVM memberikan akurasi lebih baik daripada NN.
========================================================================================================
The development of Surabaya's infrastructure was being intensified and in the process, it affects the daily activities of the community. This event had an impact on public comments or opinions about it through any media, including social media such as Twitter. Twitter was a social networking service and a microblog that allows its users to send and read text-based messages of up to 140 characters. The public opinion was an important information about their reaction to the city's development program, so it was important to be recorded and analyzed. The research was about citizen sentiment analysis using Support Vector Machine and Neural Network methods. Effective method algorithms for text classification were Support Vector Machine (SVM) and Neural Network (NN). The accuracy of SVM classification was 92.67%, while NN 80.00%. For comparison, the SVM method gives better accuracy than NN.
| Item Type: | Thesis (Masters) |
|---|---|
| Additional Information: | RTSt 006.4 Rey a-1 3100018078942 |
| Uncontrolled Keywords: | Analisis Sentimen, Neural Network, Infrastruktur, Klasifikasi, Support Vector Machine, Surabaya, Twitter |
| Subjects: | Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | Zakya Reyhana |
| Date Deposited: | 14 Feb 2019 07:07 |
| Last Modified: | 27 Jan 2021 06:54 |
| URI: | http://repository.its.ac.id/id/eprint/58144 |
Actions (login required)
 |
View Item |