Classification of Hate Speech Against Cak Nun on Twitter Multinomial Naive Bayes

Irfan Aufa Fadilla

Abstract


This research aims to identify hate speech against Cak Nun on Twitter social media using the Multinomial Naive Bayes method focusing on text pre-processing. Pre-processing involves case folding, tokenization, stopword removal, and stemming to improve classification accuracy. The tweet data taken from Cak Nun's Twitter account was analyzed to measure the level of hatred using the Multinomial Naive Bayes classification model. The case folding process is used to convert all text into lowercase letters, tokenization is performed to break the text into tokens that can be processed, stopword removal aims to remove common words that do not contribute significantly to sentiment analysis, and stemming is implemented to convert words into their basic form. The results show that pre-processing improves classification performance, achieving an accuracy of 85.135%. The findings contribute to creating a more positive and safe social media environment.


Full Text:

PDF

References


[1] Y. Rohmiyati, "Analisis Penyebaran Informasi Pada Sosial Media", anuva jurnal kajian budaya perpustakaan dan informasi, vol. 2, no. 1, p. 29, 2018, https://doi.org/10.14710/anuva.2.1.29-42.

[2] K. Antariksa, Y. Wp, & E. Ernawati, "Klasifikasi Ujaran Kebencian Pada Cuitan Dalam Bahasa Indonesia", jurnal buana informatika, vol. 10, no. 2, p. 164, 2019, https://doi.org/10.24002/jbi.v10i2.2451.

[3] O. Rahman, G. Abdillah, & A. Komarudin, "Klasifikasi Ujaran Kebencian Pada Media Sosial Twitter Menggunakan Support Vector Machine", jurnal resti (rekayasa sistem dan teknologi informasi), vol. 5, no. 1, p. 17-23, 2021, https://doi.org/10.29207/resti.v5i1.2700.

[4] I. Huda, “Implementasi Natural Language Processing (NLP) untuk Aplikasi Pencarian Lokasi”, Sekolah Vokasi Universitas Gadjah Mada, Vol. 3, No. 2, 2019.

[5] E. Ningrum and A. Widodo, "Implementasi Metode Multinomial Naïve Bayes Classifier Untuk Analisis Sentimen", journal of fundamental mathematics and applications (jfma), vol. 1, no. 2, p. 128, 2018, https://doi.org/10.14710/jfma.v1i2.18.

[6] A. Rahman, Wiranto, & A. Doewes, "Online News Classification Using Multinomial Naive Bayes." Jurnal Ilmiah Teknologi dan Informasi, Vol. 6, No. 1, June 2017.

[7] B. Hakim, "Analisa Sentimen Data Text Pre-processing Pada Data Mining Dengan Menggunakan Machine Learning", Jbase - Journal of business and audit information systems, vol. 4, no. 2, 2021, https://doi.org/10.30813/jbase.v4i2.3000.

[8] A. Rinandyaswara, Y. A. Sari, & M. T. Furqon, "Pembentukan Daftar Stopword Menggunakan Term Based Random Sampling pada Analisis Sentimen dengan Metode Naïve Bayes (Studi Kasus: Kuliah Daring di Masa Pandemi)." Jurnal Teknologi Informasi dan Ilmu Komputer, Vol. 9, No. 4, Agustus 2022.

[9] L. F. Narulita, "Analisa Sentimen Pada Tinjauan Buku Dengan Algoritma K-Nearest Neighbour", Konvergensi, vol. 13, no. 2, 2019, https://doi.org/10.30996/konv.v13i2.2758.

[10] N. A. Susanti, M. Walid, & Hoiriyah, "Klasifikasi Data Tweet Ujaran Kebencian di Media Sosial Menggunakan Naive Bayes Classifier." Jurnal Mahasiswa Teknik Informatika, Vol. 6, No. 2, September 2022.

[11] W. Hidayat, M. Ardiansyah, & A. Setyanto, "Pengaruh Algoritma Adasyn Dan Smote Terhadap Performa Support Vector Machine Pada Ketidakseimbangan Dataset Airbnb", Edumatic: Jurnal Pendidikan Informatika, vol. 5, no. 1, p. 11-20, 2021, https://doi.org/10.29408/edumatic.v5i1.3125.




DOI: https://doi.org/10.18860/jocdas.v1i1.25249

DOI (PDF): https://doi.org/10.18860/jocdas.v1i1.25249.g10994

Refbacks

  • There are currently no refbacks.