Makine Öğrenimi Kullanarak Türkçe Siber Zorbalık Tweetlerini Tespit Etme

Year 2024, Volume: 12 Issue: 3, 1410 - 1428, 31.07.2024

Yavuz Selim Balcıoğlu

https://doi.org/10.29130/dubited.1379657

Abstract

Siber zorbalık, çevrimiçi nefret söylemi ve tacizle bireylerin maruz kaldığı bir suç biçimidir ve sosyal medyanın büyümesiyle yaygınlık kazanmıştır. Mevcut literatürde, özellikle Türkçe dışındaki dillerde siber zorbalık tespiti için belirgin bir eksiklik bulunmaktadır. Bu çalışma, Türkçe tweet'lerde otomatik siber zorbalık tespiti için bir yöntem önermektedir. Önerilen model, Destek Vektör Makinesi ve Rastgele Orman sınıflandırma algoritmalarını içerir. Model, Twitter'dan alınan etiketli gerçek dünya verisiyle eğitilmiştir. Türk, dilinin, özelliklerini ele almak için Zemberek-NLP adlı bir doğal dil işleme aracı kullanılmıştır. Bu, araç, dilin, nüanslarını, ele alarak, tespit modelinin doğruluğunu artırır. Bu çalışma, Türkçe'deki siber zorbalık tespiti için yenilikçi bir yaklaşım sunarak, siber zorbalıkla mücadeleye katkıda bulunmayı hedeflemektedir.

Keywords

Siber Zorbalık Tespiti, Türkçe Sosyal Medya, Makine Öğrenimi, Destek Vektör Makinesi (SVM), Random Forest (RF) Sınıflandırıcı

Detecting Turkish Cyberbullying Tweets Using Machine Learning

Abstract

Cyberbullying is a form of crime where individuals are subjected to online hate speech and harassment, and its prevalence has increased with the growth of social media. There is a noticeable gap in the current literature, especially for cyberbullying detection in languages other than English. This study proposes a method for automatic cyberbullying detection in Turkish tweets. The proposed model incorporates the Support Vector Machine and Random Forest classification algorithms. The model has been trained on labeled real-world data sourced from Twitter. To address the characteristics of the Turkish language, a natural language processing tool called Zemberek-NLP has been used. This tool captures the nuances of the language, enhancing the accuracy of the detection model. This research aims to contribute to the fight against cyberbullying by presenting an innovative approach to detecting it in Turkish.

Keywords

Cyberbullying Detection, Turkish Social Media, Machine Learning, Support Vector Machine (SVM), Random Forest (RF) Classifier

References

• [1] A. Mishrif and A. Khan, “Causal Analysis of Company Performance and Technology Mediation in Small and Medium Enterprises During COVID-19,” Journal of the Knowledge Economy, Oct. 2022,
• [2] Erdal Özbay, “Transformatör-Tabanlı Evrişimli Sinir Ağı Modeli Kullanarak Twıtter Verisinde Saldırganlık Tespiti,” Selcuk University Journal of Engineering, Science and Technology, pp. 986–1001, Dec. 2022
• [3] Ayça Balmumcu and Hilal Yüceyılmaz, “Investigation of Cyberbullying and Cyber Victimization Level of Young Women,” Afyon Kocatepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi dergisi, May 2023
• [4] A. Blanchard and T. Horan, “Virtual Communities and Social Capital,” Social Dimensions of Information Technology: Issues for the New Millennium, 2000. https://www.igi-global.com/chapter/virtual-communities-social-capital/29107 (accessed Mar. 31, 2020).
• [5] L. Cheng, K. Shu, S. Wu, Y. N. Silva, D. L. Hall, and H. Liu, “Unsupervised Cyberbullying Detection via Time-Informed Gaussian Mixture Model,” arXiv.org, Aug. 06, 2020. https://arxiv.org/abs/2008.02642 (accessed Oct. 22, 2023).
• [6] S. N. Firdaus, C. Ding, and A. Sadeghian, “Retweet Prediction based on Topic, Emotion and Personality,” Online Social Networks and Media, vol. 25, p. 100165, Sep. 2021
• [7] S. C. S. Caravita, B. Colombo, S. Stefanelli, and R. Zigliani, “Emotional, psychophysiological and behavioral responses elicited by the exposition to cyberbullying situations: Two experimental studies,” Psicología Educativa, vol. 22, no. 1, pp. 49–59, Jun. 2016
• [8] Rüstem Göktürk HAYLI and Yrd. Doç. Dr.yüksel ÇIRAK, “Siber Zorba Olan ve Olmayan Ergenlerin Yordanmasında Siber Mağduriyet, Akran Zorbalığı ve Karanlık Üçlünün Rolü,” Journal of Inonu University Faculty of Education, vol. 24, no. 1, pp. 420–448, May 2023
• [9] K. Jordan, “From Social Networks to Publishing Platforms: A Review of the History and Scholarship of Academic Social Network Sites,” Frontiers in Digital Humanities, vol. 6, Mar. 2019,
• [10] I. F. Kilincer, F. Ertam, and A. Sengur, “Machine Learning Methods for Cyber Security Intrusion Detection: Datasets and Comparative Study,” Computer Networks, vol. 188, p. 107840, Jan. 2021
• [11] M. C. Martínez-Monteagudo, B. Delgado, Á. Díaz-Herrero, and J. M. García-Fernández, “Relationship between suicidal thinking, anxiety, depression and stress in university students who are victims of cyberbullying,” Psychiatry Research, vol. 286, p. 112856, Apr. 2020
• [12] A. Muneer and S. M. Fati, “A Comparative Analysis of Machine Learning Techniques for Cyberbullying Detection on Twitter,” Future Internet, vol. 12, no. 11, p. 187, Oct. 2020
• [13] B. A. Talpur and D. O’Sullivan, “Cyberbullying severity detection: A machine learning approach,” PLOS ONE, vol. 15, no. 10, p. e0240924, Oct. 2020
• [14] D. Olweus and S. P. Limber, “Some problems with cyberbullying research,” Current Opinion in Psychology, vol. 19, pp. 139–143, Feb. 2018
• [15] H. Vandebosch and K. Van Cleemput, “Cyberbullying among youngsters: profiles of bullies and victims,” New Media & Society, vol. 11, no. 8, pp. 1349–1371, Nov. 2009
• [16] J. Hani, M. Nashaat, M. Ahmed, Z. Emad, E. Amer, and A. Mohammed, “Social Media Cyberbullying Detection using Machine Learning,” International Journal of Advanced Computer Science and Applications, vol. 10, no. 5, 2019
• [17] M. A. Al-Garadi et al., “Predicting Cyberbullying on Social Media in the Big Data Era Using Machine Learning Algorithms: Review of Literature and Open Challenges,” IEEE Access, vol. 7, pp. 70701–70718, 2019
• [18] A. Ali and A. M. Syed, “Cyberbullying Detection using Machine Learning,” DOAJ (DOAJ: Directory of Open Access Journals), Sep. 2020
• [19] E. Raisi and B. Huang, “Cyberbullying Detection with Weakly Supervised Machine Learning,” Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017 - ASONAM ’17, 2017
• [20] M. Sadigzade and E. Nasibov, "Comparative Analysis of Count Vectorization vs TF-IDF Vectorization for Detecting Cyberbullying in Turkish Twitter Messages," in Journal of Modern Technology & Engineering, vol. 7, no. 1, 2022.
• [21] B. ERDİ, E. A. ŞAHİN, M. S. TOYDEMİR, and T. DÖKEROĞLU, “Makine Öğrenmesi Algoritmaları ile Trol Hesapların Tespiti,” Düzce Üniversitesi Bilim ve Teknoloji Dergisi, Nov. 2020,
• [22] V. Diogho and A. Paula, “Exploring Text Mining and Analytics for Applications in Public Security: an in-depth dive into a systematic literature review,” Socioeconomic Analytics, vol. 1, pp. 5–55, Jul. 2023
• [23] A. Bozyigit, S. Utku, and E. Nasiboglu, “Cyberbullying Detection by Using Artificial Neural Network Models,” 2019 4th International Conference on Computer Science and Engineering (UBMK), Sep. 2019
• [24] H. Baruah, P. Dashora, and M. K. Chaudhary, “Incidences of cyberbullying among adolescents,” Advance Research Journal Of Socıal Scıence, vol. 8, no. 2, pp. 143–149, Dec. 2017
• [25] A. Al-Marghilani, “Artificial Intelligence-Enabled Cyberbullying-Free Online Social Networks in Smart Cities,” International Journal of Computational Intelligence Systems, vol. 15, no. 1, Jan. 2022
• [26] I. Aoyama and T. L. Talbert, “Cyberbullying Internationally Increasing,” pp. 183–201, Jan. 2010
• [27] S. Skilbred-Fjeld, S. E. Reme, and S. Mossige, “Cyberbullying involvement and mental health problems among late adolescents,” Cyberpsychology: Journal of Psychosocial Research on Cyberspace, vol. 14, no. 1, Feb. 2020
• [28] M.-J. Wang, K. Yogeeswaran, N. P. Andrews, D. R. Hawi, and C. G. Sibley, “How Common Is Cyberbullying Among Adults? Exploring Gender, Ethnic, and Age Differences in the Prevalence of Cyberbullying,” Cyberpsychology, Behavior, and Social Networking, vol. 22, no. 11, pp. 736–741, Nov. 2019
• [29] M. ERDOĞDU and M. KOÇYİĞİT, “The correlation between social media use and cyber victimization: A research on generation Z in Turkey,” Connectist: Istanbul University Journal of Communication Sciences, 2021
• [30] Y. Akbulut and B. Eristi, “Cyberbullying and victimisation among Turkish University students,” Australasian Journal of Educational Technology, vol. 27, no. 7, 2011
• [31] A. ARSLAN, O. BİLGİN, and M. INCE, “Lise Öğrencilerine Yönelik Siber Zorbalık Ölçeği Geliştirme Çalışması,” OPUS Uluslararası Toplum Araştırmaları Dergisi, pp. 1–1, Jun. 2020