SUBAGIO, ARIF WIDIASAN (2024) Penggunaan Deep Learning Untuk Lexicon-based Sentiment Analysis Tragedi Kanjuruhan Pada Media Sosial Twitter. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
19081010065_cover.pdf Download (507kB) | Preview |
|
|
Text (BAB 1)
19081010065_bab1.pdf Download (164kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB 2)
19081010065_bab2.pdf Restricted to Repository staff only until 13 January 2027. Download (617kB) |
|
|
Text (BAB 3)
19081010065_bab3.pdf Restricted to Repository staff only until 13 January 2027. Download (307kB) |
|
|
Text (BAB 4)
19081010065_bab4.pdf Restricted to Repository staff only until 13 January 2027. Download (591kB) |
|
|
Text (BAB 5)
19081010065_bab5.pdf Download (11kB) | Preview |
|
|
Text (Daftar Pustaka)
19081010065_daftarpustaka.pdf Download (97kB) | Preview |
|
|
Text (Lampiran)
19081010065_lampiran.pdf Restricted to Repository staff only until 13 January 2027. Download (1MB) |
Abstract
Twitter is one of the social media platforms that is quite influential for its users in Indonesia. Many Twitter users in Indonesia post tweets about their feelings or opinions on things that happen in Indonesia, one of which is the Kanjuruhan tragedy. This final project aims to apply deep learning in performing lexicon-based sentiment analysis of the Kanjuruhan tragedy on Twitter social media. The methods used are Multilayer Percepteron (MLP) and Convolutional Neural Network (CNN). The trials carried out went through several flows such as data collection on Twitter and then cleaned. In making MLP and CNN models there are various configuration variations to get the best model so that the results given later will be more accurate. The results of this trial show that the CNN method model has better performance than the MLP method with the CNN method accuracy rate of around 87.77%, while the MLP method has an accuracy rate of around 83.9%. CNN method is proven to be one of the options to perform lexicon-based sentiment analysis.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76.6 Computer Programming Q Science > QA Mathematics > QA76.87 Neural computers T Technology > T Technology (General) |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Arif Widiasan Subagio | ||||||||||||
| Date Deposited: | 15 Jan 2024 02:36 | ||||||||||||
| Last Modified: | 15 Jan 2024 02:36 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/19822 |
Actions (login required)
 |
View Item |