Prediksi Ujaran Kebencian Berbasis Text Pada Sosial Media Menggunakan Metode Neural Network

Kristiawan Nugroho (Program Studi Magister Teknologi Informasi, Fakultas Teknologi Informasi dan Industri, Universitas Stikubank)
Endang Tjahjaningsih (Program Studi Magister Manajemen, Fakultas Ekonomi dan Bisnis , Universitas Stikubank)
Lie Liana (Program Studi Magister Manajemen, Fakultas Ekonomi dan Bisnis , Universitas Stikubank)
Raden Mohamad Herdian Bhakti (Program Studi Teknik Informatika, Fakultas Teknik, Universitas Muhadi Setiabud)

Jurnal Ilmiah Intech : Information Technology Journal of UMUS
Vol 5 No 1 (2023): Mei

Currently information technology has helped in various forms of human life. They can communicate with each other through various electronic media, including using social media. The number of social media users is increasing from year to year in Indonesia. However, the development of the use of social media has also resulted in various problems, including hate speech, which will eventually lead to legal consequences. Various methods have been taken to limit the development of hate speech, including by blocking users who write hate speech on social media applications. Limiting the use of social media for hate speech can be more optimally carried out by detecting text-based words that have the potential to become hate speech. This study uses the Neural Network (NN) method to predict words that contain hatespeech on social media with an accuracy rate of 73% better than other methods such as Decission Tree and K-Nearest Neighbor (KNN) which only achieve an accuracy rate of 68.5 %.