Identifikasi Ujaran Kebencian pada Twitter Menggunakan Metode Convolutional Neural Network (CNN)
Abstract
Abstrak-Ujaran kebencian merupakan suatu tindak kejahatan yang dijadikan sebagai alat provokasi ke suatu kelompok, yang dimana suatu kelompok tersebut di bagi ke dalam beberapa kelompok seperti ras, warna kulit, gender, cacat, dan kewarnganegaraan. Ujaran kebencian yang terjadi biasanya dalam bentuk kalimat maupun gambar dan disebarluaskan melalui internet. Media sosial Twitter merupakan jejaring sosial yang banyak menampung opini masyarakat tentang apapun yang dapat di sebarluaskan dengan cepat diterima oleh pengguna Twitter yang lain. Pada penelitian sebelumnya akurasi yang didapat sebesar 79% dengan menggunakan metode Convolutional Neural Network. Berdasarkan penelitian tersebut, maka dalam penelitian ini dikembangkan sebuah sistem untuk mengidendentifikasi ujaran kebencian dan diklasifikasikan menggunakan metode Convolutional Neural Network dengan membandingkan beberapa hyperparameter tuning dan menghasilkan hyperparameter tuning terbaik untuk model CNN yaitu dropout 0.3 dan learning rate 0.001 yang menghasilkan nilai akurasi model CNN sebesar 81%.
Kata kunci-ujaran kebencian, convolutional neural network (CNN), hyperparameter tuning
References
N. Zuraya, “Virtual Police: Konten Ujaran Kebencian Terbanyak di Twitter,” Republika, 2021. https://www.republika.co.id/berita/qputx3383/emvirtual-policeem-konten-ujaran-kebencian-terbanyak-di-twitter.
P. Badjatiya, S. Gupta, M. Gupta, and V. Varma, “Deep Learning for Hate Speech Detection in Tweets,” vol. 2, no. 2, pp. 427–431, 2017, doi: 10.18653/v1/e17-2068.
R. Alshalan and H. Al-Khalifa, “A deep learning approach for automatic hate speech detection in the saudi twittersphere,” Appl. Sci., vol. 10, no. 23, pp. 1–16, 2020, doi: 10.3390/app10238614.
A. Gune and M. Nene, “Convolutional Neural Networks for Text Categorization with Latent Semantic Analysis,” 2017 Int. Conf. Energy, Commun. Data Anal. Soft Comput., pp. 499–503, 2017.
B. Gamback and U. K. Sikdar, “Using Convolutional Neural Networks to Classify Hate-Speech,” no. 7491, pp. 85–90, 2017, doi: 10.18653/v1/w17-3013.
J. Cai, J. Li, W. Li, and J. Wang, “Deeplearning Model Used in Text Classification,” 2018 15th Int. Comput. Conf. Wavelet Act. Media Technol. Inf. Process. ICCWAMTIP 2018, pp. 123–126, 2019, doi: 10.1109/ICCWAMTIP.2018.8632592.
S. Ro, “Hate Speech Detection in the Indonesian Language: A Dataset and Preliminary Study,” pp. 473–481, 1999, [Online]. Available: https://support.twitter.eom/articles/l.
G. Koushik, K. Rajeswari, and S. K. Muthusamy, “Automated hate speech detection on Twitter,” Proc. - 2019 5th Int. Conf. Comput. Commun. Control Autom. ICCUBEA 2019, 2019, doi: 10.1109/ICCUBEA47591.2019.9128428.
A. Marpaung, R. Rismala, and H. Nurrahmi, “Hate Speech Detection in Indonesian Twitter Texts using Bidirectional Gated Recurrent Unit,” KST 2021 - 2021 13th Int. Conf. Knowl. Smart Technol., pp. 186–190, 2021, doi: 10.1109/KST51265.2021.9415760.
O. Istaiteh, R. Al-Omoush, and S. Tedmori, “Racist and Sexist Hate Speech Detection: Literature Review,” 2020 Int. Conf. Intell. Data Sci. Technol. Appl. IDSTA 2020, pp. 95–99, 2020, doi: 10.1109/IDSTA50958.2020.9264052.
H. Mohaouchane, A. Mourhir, and N. S. Nikolov, “Detecting Offensive Language on Arabic Social Media Using Deep Learning,” 2019 6th Int. Conf. Soc. Networks Anal. Manag. Secur. SNAMS 2019, pp. 466–471, 2019, doi: 10.1109/SNAMS.2019.8931839.
A. H. Om, “Deep Learning Framework based on Word2Vec and CNN for Users Interests Classification,” 2017.
E. Fehn Unsvåg and B. Gamback, “The Effects of User Features on Twitter Hate Speech Detection,” no. 2012, pp. 75–85, 2019, doi: 10.18653/v1/w18-5110.
B. P. Putra, B. Irawan, C. Setianingsih, F. T. Elektro, U. Telkom, and D. Learning, “Convolutional Neural Network Pada Gambar Hatespeech Detection Using Convolutional Neural Network Algorithm Based on Image,” no. 3, 2019.
N. Amruthmath, “Why balancing your data set is important?,” 2021. https://www.iamnagdev.com/?p=863.
J. Patihullah and E. Winarko, “Hate Speech Detection for Indonesia Tweets Using Word Embedding And Gated Recurrent Unit,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 13, no. 1, p. 43, 2019, doi: 10.22146/ijccs.40125.
S. Symeonidis, D. Effrosynidis, and A. Arampatzis, “A comparative evaluation of pre-processing techniques and their interactions for twitter sentiment analysis,” Expert Syst. Appl., vol. 110, pp. 298–310, 2018, doi: 10.1016/j.eswa.2018.06.022.
A. M. Ramadhani and H. S. Goo, “Twitter sentiment analysis using deep learning models,” 2020 IEEE 17th India Counc. Int. Conf. INDICON 2020, 2020, doi: 10.1109/INDICON49873.2020.9342279.
A. Amalanathan and P. Nikil, “Data Preprocessing In Sentiment Analysis Using Twitter Data,” Int. Educ. Appl. Res. J., vol. 03, no. July, pp. 89–92, 2019.
S. Sivakumar, L. S. Videla, T. Rajesh Kumar, J. Nagaraj, S. Itnal, and D. Haritha, “Review on Word2Vec Word Embedding Neural Net,” Proc. - Int. Conf. Smart Electron. Commun. ICOSEC 2020, no. Icosec, pp. 282–290, 2020, doi: 10.1109/ICOSEC49089.2020.9215319.
M. Wen, Y. Chen, H. Wu, S. Hou, and Y. Yang, “Automatic Classification of Government Texts Based on Improved CNN and Skip-gram Models,” in 2021 2nd International Conference on Information Science and Education (ICISE-IE), Nov. 2021, pp. 578–583, doi: 10.1109/ICISE-IE53922.2021.00138.
T. Shoryu, L. Wang, and R. Ma, “A Deep Neural Network Approach using Convolutional Network and Long Short Term Memory for Text Sentiment Classification,” Proc. 2021 IEEE 24th Int. Conf. Comput. Support. Coop. Work Des. CSCWD 2021, pp. 763–768, 2021, doi: 10.1109/CSCWD49262.2021.9437871.
N. M. Aszemi and P. D. D. Dominic, “Hyperparameter optimization in convolutional neural network using genetic algorithms,” Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 6, pp. 269–278, 2019, doi: 10.14569/ijacsa.2019.0100638.
N. L. Beebe, L. A. Maddox, L. Liu, and M. Sun, “Sceadan: Using Concatenated N-Gram Vectors for Improved File and Data Type Classification,” no. c, 2013.
S. Y. Sen and N. Ozkurt, “Convolutional Neural Network Hyperparameter Tuning with Adam Optimizer for ECG Classification,” Proc. - 2020 Innov. Intell. Syst. Appl. Conf. ASYU 2020, no. 978, 2020, doi: 10.1109/ASYU50717.2020.9259896.
