APPLICATION OF DATA MINING TO CLASSIFY HATE SPEECH ON SOCIAL MEDIA BY USING THE K NEAREST NEIGHBOR ALGORITHM
Abstract
Abstract: Social media is one of the biggest sources of information that we can get right now. However, in the use and dissemination of information, there are still many social media users who spread information or hateful words (Hate Speech). Therefore classification needs to be done to reduce the appearance of hate speech sentences with K Nearest Neighbor. K Nearest Neighbor Algorithm classifies based on the results of learning on the object being carried out. In the research carried out the KNN algorithm succeeded in classifying the Hate Speech on the given tweet data.
Keywords: K neares neighbor, Classification, Data Mining, Hate Speech, Social Media
Abstrak: Sosial media fungsinya pada saat ini merupakan salah satu sumber informasi terbesar yang dapat kita dapatkan. Namun, dalam penggunaan dan penyebaran informasinya, masih banyak pengguna sosial media yang menyebarkan informasi atau kata-kata berbau kebencian (Hate Speech). Untuk itu klasifikasi perlu dilakukan untuk mengurangi munculnya kalimat berbau hate speech dengan K Nearest Neighbor. Algoritma K Nearest Neighbor mengklasifikasikan berdasarkan hasil dari pembelajaran terhadap objek yang dilakukan. Pada penelitian yang dilakukan algoritma KNN berhasil melakukan klasifikasi Hate Speech pada data tweet yang diberikan.
Kata Kunci: K Nearest Neighbor, Klasifikasi, Data Mining, Ujaran Kebencian, Sosial Media
Full Text:
PDFDOI: https://doi.org/10.24114/jh.v10i1.14144
Article Metrics
Abstract view : 353 timesPDF - 318 times
Refbacks
- There are currently no refbacks.
Copyright (c) 2019 Windania Purba, Fando Marehitno Salim, Antoni Antoni, Yuni Suhendrik, Jeanie Winata
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Jurnal Handayani PGSD FIP UNIMED is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.