Clustering Community Cyberbullying Comments on Instagram based on K-Means Clustering
##plugins.themes.bootstrap3.article.main##
Abstract
Cyberbullying has become a serious problem on social media platforms like Instagram. In an effort to overcome this problem, this study aims to classify cyberbullying comments made by Instagram users. The method used in this study is K-Means Clustering, which is a grouping technique commonly used in data analysis. The comment data collected from Instagram is then analyzed using the K-Means Clustering algorithm to identify patterns and groups of similar comments. The findings from this study can provide a better understanding of the types and characteristics of cyberbullying comments that often appear on Instagram. By knowing groups of similar comments, prevention and response measures can be designed more effectively. In addition, the results of clustering can also help in the development of automatic detection algorithms to identify cyberbullying comments on social media platforms. Based on the evaluation carried out on the clustering results with a silhouette score = 0.690152, namely in cluster C1, which is a negative cluster. So, the most dominant cyberbullying comments are negative comments.
##plugins.themes.bootstrap3.article.details##
Candra, R. M., & Rozana, A. N. (2020). Klasifikasi Komentar Bullying pada Instagram Menggunakan Metode K-Nearest Neighbor. 5(1), 45–52.
Djaballah, K. A., Boukhalfa, K., & Boussaid, O. (2019). Sentiment Analysis of Twitter Messages using Word2vec by Weighted Average. 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019, 223–228. https://doi.org/10.1109/SNAMS.2019.8931827
Hasdyna, N., & Dinata, R. K. (2020). Analisis Matthew Correlation Coefficient pada K-Nearest Neighbor dalam Klasifikasi Ikan Hias. INFORMAL: Informatics Journal, 5(2), 57. https://doi.org/10.19184/isj.v5i2.18907
Jardim, S., Mora, C., Jardim, S., & Mora, C. (2022). ScienceDirect ScienceDirect Customer reviews sentiment-based analysis and clustering for tourism services and products development or Customer reviews and clustering for positioning market-oriented tourism services and products development or positioning. Procedia Computer Science, 196(2021), 199–206. https://doi.org/10.1016/j.procs.2021.12.006
Khaira, U., Johanda, R., Eko, P., Utomo, P., Suratno, T., & Info, A. (2020). Sentiment Analysis of Cyberbullying on Twitter Using SentiStrength. 3(1), 21–27.
Liu, S. (2016). Sentiment Clustering with Topic and Temporal Information from Large Email Dataset. Paclic 30, 363–371.
Method, M., Triyana, R., Putra, O. V., Pradhana, F. R., & Gontor, U. D. (n.d.). Deteksi Cyberbullying Pada Tweet Berbahasa Inggris Dengan Metode Support Vector Machine. (2017) 98–103.
Nainggolan, R., Adline, F., Tobing, T., Harianja, E. J. G., Akuntansi, K., Indonesia, U. M., Informatika, P., & Nusantara, U. M. (2023). Analysis Sentiment in Bukalapak Comments with K-Means Clustering Method. 9(2), 87–92.
Ningtyas, A. M., & Herwanto, G. B. (2018). The Influence of Negation Handling on Sentiment Analysis in Bahasa Indonesia. Proceedings of 2018 5th International Conference on Data and Software Engineering, ICoDSE 2018, November 2018. https://doi.org/10.1109/ICODSE.2018.8705802
Patihullah, J., & Winarko, E. (2019). Hate Speech Detection for Indonesia Tweets Using Word Embedding And Gated Recurrent Unit. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 13(1), 43. https://doi.org/10.22146/ijccs.40125
Prastyo, P. H., Sumi, A. S., Dian, A. W., & Permanasari, A. E. (2020). Tweets Responding to the Indonesian Government’s Handling of COVID-19: Sentiment Analysis Using SVM with Normalized Poly Kernel. Journal of Information Systems Engineering