Evaluation of Society Response to Violence against Women in Turkey via Twitter using Topic Modeling

Abstract

In recent times, people's reactions to violence against women, harassment and murder have been shared more and more, thanks to social media. This, in turn, led to the organization of people and increased awareness of violence against women. Inspired by this study, it focuses on subject modeling techniques to determine people's perspectives on violence against women, which is growing day by day. Opinions from users about violence against women are collected using the social media platform Twitter in order to analyze the reaction of the society. After the preprocessing stage, Turkish tweets are analyzed using Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA), Hierarchical Dirichlet Process (HDP), Non-Negative Matrix Factorization (NMF) techniques. The results of the experiment show that the LDA technique significantly reveals the reaction of the society to violence against women and social awareness in Turkey.

Keywords

• Violence aganist/to Women
• Opinion Mining
• Latent Dirichlet Allocation
• Social Media Mining
• Topic Modeling

References

1. [1] Gencer M.Z., Ağırman E., Arıca S, 2019. İstanbul ilinde kadına yönelik şiddet sıklığı ve kadınların şiddet algısı. Ahi Evran Tıp Dergisi, 3(1), pp. 18-25.
2. [2] Özkan G, 2017. Kadına yönelik şiddet-aile içi şiddet ve konuya ilişkin uluslararası metinler üzerine bir inceleme. Hacettepe Hukuk Fakültesi Dergisi, 7(1), pp. 533-564.
3. [3] World Health Organization Global and Regional Estimates of Violence Against Women: Prevalence and Health Effects of İntimate Partner Violence and Non-Partner Sexual Violence 2013. http://apps.who.int/iris/bitstream/handle/10665/85239/?sequence=1. (Access date: 08 March 2021).
4. [4] World Health Organization. World Report on Violence and Health 2002. https://www.who.int/violence_injury_prevention/violence/world_report/en/summary_en.pdf (Access date: 08 March 2021).
5. [5] Okazaki M., Matsuo Y., 2008. Semantic Twitter: Analyzing tweets for real-time event notification. Paper presented at International Conference on Social Software, Cork, Ireland, 3–4 March, pp. 63–74.
6. [6] Pang B., Lee L., 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2, pp. 1–135.
7. [7] Landauer T.K., Foltz P.W., Laham D., 1998. An introduction to latent semantic analysis. Discourse Processes, 25(2-3), pp. 259-284.
8. [8] Dumais S.T., 2004. Latent semantic analysis. Annual Review of Information Science and Technology, 38(1), pp. 188-230.

9. [9] Landauer T.K., McNamara D.S., Dennis S., Kintsch W., 2013. Handbook of Latent Semantic Analysis, 2nd ed. Psychology Press, New York, USA.
10. [10] Blei D.M., Ng A.Y., Jordan M.I., 2003. Latent Dirichlet allocation. The Journal of Machine Learning Research, 3, pp. 993-1022.
11. [11] Hoffman M., Bach F.R., Blei D.M., 2010. Online learning for latent dirichlet allocation. Advances in Neural Information Processing Systems, 23, pp. 856-864.
12. [12] Wang X., Grimson E., 2007. Spatial latent Dirichlet allocation. Paper presented at Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 3-6 December, pp. 1577-1584.
13. [13] Teh Y.W., Jordan M.I., Beal M.J., Blei D.M., 2006. Hierarchical Dirichlet processes. Journal of the American Statistical Association, 101(476), pp. 1566-1581.
14. [14] Wang C., Paisley J., Blei D.M., 2011. Online variational inference for the hierarchical Dirichlet process. Paper presented at International Conference on Artificial Intelligence and Statistics, Lauderdale, FL, USA, 11-13 April, pp. 752-760.
15. [15] Paisley J., Wang C., Blei D.M., Jordan M.I., 2014. Nested hierarchical Dirichlet processes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(2), pp. 256-270.
16. [16] Lee D.D., Seung H.S., 1999. Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), pp. 788-791.
17. [17] Xu W., Liu X., Gong Y., 2003. Document clustering based on non-negative matrix factorization. Paper presented at International ACM SIGIR Conference on Research and Development in Information Retrieval, Toronto, Canada, 28 July- 1 August, pp. 267-273.
18. [18] Hoyer P.O., 2004. Non-negative matrix factorization with sparseness constraints. Journal of Machine Learning Research, 5(9), pp. 1457–1469.
19. [19] Rodríguez-Rodríguez I., Rodríguez J.V., Pardo-Quiles D.J., Heras-González P., Chatzigiannakis I, 2020. Modeling and forecasting gender-based violence through machine learning techniques. Applied Sciences, 10(22), pp. 1-22.
20. [20] Xue J., Chen J., Chen C., Hu R., Zhu T., 2020. The hidden pandemic of family violence during COVID-19: Unsupervised learning of tweets. Journal of Medical Internet Research, 22(11), pp. 1-11.
21. [21] Bello H.J., Palomar N., Gallego E., Navascués L.J., Lozano C., 2020. Machine learning to study the impact of gender-based violence in the news media. arXiv preprint arXiv:2012.07490, pp. 1-17.
22. [22] Amusa L.B., Bengesai A.V., Khan H.T., 2020. Predicting the vulnerability of women to intimate partner violence in South Africa: Evidence from tree-based machine learning techniques. Journal of Interpersonal Violence, 2020, pp. 1-18.
23. [23] Xue J., Chen J., Gelles R., 2019. Using data mining techniques to examine domestic violence topics on Twitter. Violence and Gender, 6(2), pp. 105-114.
24. [24] Frenda S., Ghanem B., Montes-y-Gómez M., Rosso P., 2019. Online hate speech against women: Automatic identification of misogyny and sexism on twitter. Journal of Intelligent and Fuzzy Systems, 36(5), pp. 4743-4752.