Syah, Syamaidzar Adani (2026) Analisis Intoleransi Terhadap Fenomena Sound Horeg Pada Media X Dengan Metode Svm dan Knn. Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Ringkasan / Abstract)
Abstract skripsi.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (333kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka Skripsi.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (189kB) |
|
Text (Bab 1 pendahuluan)
pendahuluan skripsi.pdf Available under License Creative Commons Attribution Share Alike. Download (480kB) |
|
Text (Laporan Lengkap)
REVISI7_final_bendel revisi sipora.pdf - Submitted Version Restricted to Registered users only Download (3MB) | Request a copy |
Abstract
The “sound horeg” phenomenon on platform X has given rise to a wide range of speech, ranging from rational criticism to intolerant speech that is difficult to distinguish automatically because it is often disguised by subtle linguistic strategies such as sarcasm, idioms, and curses. This study analyzes intolerant discourse in the “sound horeg” phenomenon using Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Ensemble (2:1 soft voting) models, based on 1,393 Indonesian-language tweets labeled using a hybrid method (lexicon and manual) with a Cohen’s Kappa of 0.655. Evaluation results on 279 test data points showed that the Ensemble model achieved the highest accuracy at 63.80%, followed by SVM at 63.44% and KNN at 51.25%, with the dominant error pattern being 58.82% of negative statements classified as neutral. An in-depth analysis through the extraction of discriminative keywords validated that the “sound horeg” discourse reflects complex digital social tensions and consists of three interrelated dimensions: the diversity of forms of negative speech, the dimension of physical and health disturbances, and the dimension of conflicts over cultural values and traditions, with the political dimension emerging as an additional finding from the extraction of discriminative keywords. Consequently, the limitations of TF -IDF model in capturing the gray areas of intolerance reflects the complexity of X media users’ expressions
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | Sound Horeg, Analisis Intoleransi, Support Vector Machine, K-Nearest Neighbor, Ensemble Learning, TF-IDF, Media Sosial X | ||||||
| Subjects: | 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 461 - Sistem Informasi 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 463 - Teknik Perangkat Lunak 500 - Rumpun Ilmu Bahasa > 520 - Ilmu Bahasa > 521 - Ilmu Linguistik |
||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika > Tugas Akhir | ||||||
| Depositing User: | Syamaidzar Adani Syah | ||||||
| Date Deposited: | 29 Jul 2026 06:11 | ||||||
| Last Modified: | 29 Jul 2026 06:12 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/58809 |
Actions (login required)
 |
View Item |
