Ramadhani, Akira Permata (2024) Klasifikasi Cyberbullying Pada Komentar Instagram Akun Plesbol.inc Menggunakan Naive Bayes. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
19082010088-cover.pdf Download (3MB) |
|
Text (Bab 1)
19082010088-bab1.pdf Download (187kB) |
|
Text (Bab 2)
19082010088-bab2.pdf Restricted to Repository staff only until 20 June 2028. Download (330kB) |
|
Text (Bab 3)
19082010088-bab3.pdf Restricted to Repository staff only until 20 June 2028. Download (155kB) |
|
Text (Bab 4)
19082010088-bab4.pdf Restricted to Repository staff only until 20 June 2028. Download (1MB) |
|
Text (Bab 5)
19082010088-bab5.pdf Download (9kB) |
|
Text (Daftar Pustaka)
19082010088-daftarpustaka.pdf Download (234kB) |
|
Text (Lampiran)
19082010088-lampiran.pdf Restricted to Repository staff only until 20 June 2028. Download (111kB) |
Abstract
Cyberbullying is an action related to the use of digital technology to intentionally hurt, humiliate or bully other people online. This research focuses on the classification of cyberbullying comments on social media, especially Instagram comments, where many parties who then become a group of people who don't like something will come together to provide negative opinions and comments, which can cause lowered self-confidence and other bad impacts for other users and account owner. Based on this problem, Instagram comments regarding cyberbullying were classified as an effort to prevent this action. The data used in this research is 2000 data taken from social media Instagram, where this data will go through various processes so that it can be executed. The processes involved include data labeling, text preprocessing, wordcloud visualization, data sharing, TF-IDF, naïve Bayes classification, and model evaluation. In this research, the Naïve Bayes method was used which uses all types of naïve Bayes, namely, Multinomial, Bernoulli, and Gaussian. This research used two classes, namely the Bully class with 898 data and the Not Bully class with 1102 data. Data sharing uses two methods, namely, cross-validation (90:10) and holdout (70:30). This research uses 12 scenarios and based on the results of the tests that have been carried out, the scenario chosen is the holdout scenario (70:30) with an accuracy value of 84%, a precision value of 84%, a recall of 84%, and an f1-score of 84%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) > T58.6-58.62 Management Information Systems | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | SI Akira | ||||||||||||
| Date Deposited: | 21 Jun 2024 03:15 | ||||||||||||
| Last Modified: | 21 Jun 2024 03:15 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/24647 |
Actions (login required)
 |
View Item |