Detection and Classification of Hatespeech on Twitter Using Convolutional Neural Network (CNN) - Dalam bentuk buku karya ilmiah
MUHAMMAD RAFI YANAPUTERANTO
Informasi Umum
Kode
24.04.5784
Klasifikasi
006.32 - Neural networks, perceptrons, connectionism, neural computers
Jenis
Karya Ilmiah - Skripsi (S1) - Reference
Subjek
Neural Networks
Dilihat
77 kali
Informasi Lainnya
Abstraksi
Hate speech is any form of communication that<br /> attacks a person or group based on attributes such as race,<br /> religion, ethnicity, gender, sexual orientation, nationality, or<br /> other attributes. It can be verbal, written, or nonverbal. Hate<br /> speech can be dangerous because it can lead to violence,<br /> discrimination, and social exclusion for certain demographics of<br /> people. Social media platforms have become the main platforms<br /> for spreading hate speech. Social media companies can combat<br /> and minimize the spread of hate speech by educating their users<br /> about the adverse effects of hate speech and developing a system<br /> to detect, identify, and remove contents that contain hate speech.<br /> Convolutional neural network (CNN) is an algorithm that can<br /> be used to determine whether a tweet is hate speech or not. The<br /> proposed method could facilitate the identification and<br /> detection of hate speech on social media platforms. Feature<br /> extraction is performed using TF-IDF, with FastText used as<br /> feature expansion. In this study, there are three test scenarios<br /> that were applied, where we included baselines with TF-IDF,<br /> FastText implementation, and the best hyperparameter search.<br /> The results showed a significant improvement in accuracy, with<br /> the third scenario achieving an accuracy of 86.87%, an increase<br /> of about 9.84% compared to the results in the first scenario,<br /> which got a result of 77.03%, and the second scenario, which got<br /> a result of 85.03%.
- CII1F4 - ALGORITMA PEMROGRAMAN
- CII4O3 - ANALISIS JEJARING SOSIAL
- CII3P3 - PEMODELAN DAN SIMULASI
Koleksi & Sirkulasi
Tersedia 1 dari total 1 Koleksi
Anda harus log in untuk mengakses flippingbook
Pengarang
| Nama | MUHAMMAD RAFI YANAPUTERANTO |
| Jenis | Perorangan |
| Penyunting | Erwin Budi Setiawan |
| Penerjemah |
Penerbit
| Nama | Universitas Telkom, S1 Informatika |
| Kota | Bandung |
| Tahun | 2024 |
Sirkulasi
| Harga sewa | IDR 0,00 |
| Denda harian | IDR 0,00 |
| Jenis | Non-Sirkulasi |
