Towards Automated Sexual Violence Report Tracking


  • Naeemul Hassan University of Maryland, College Park
  • Amrit Poudel University of Mississippi
  • Jason Hale University of Mississippi
  • Claire Hubacek University of Mississippi
  • Khandaker Tasnim Huq Khulna University of Engineering and Technology
  • Shubhra Kanti Karmaker Santu Massachusetts Institute of Technology
  • Syed Ishtiaque Ahmed University of Toronto



Warning: This paper may contain trigger words that might be uncomfortable to some readers. Tracking sexual violence is a challenging task. In this paper, we present a supervised learning-based automated sexual violence report tracking model that is more scalable, and reliable than its crowdsource based counterparts. We define the sexual violence report tracking problem by considering victim, perpetrator contexts and the nature of the violence. We find that our model could identify sexual violence reports with a precision and recall of 80.4% and 83.4%, respectively. Moreover, we also applied the model during and after the #MeToo movement. Several interesting findings are discovered which are not easily identifiable from a shallow analysis.




How to Cite

Hassan, N., Poudel, A., Hale, J., Hubacek, C., Huq, K. T., Karmaker Santu, S. K., & Ahmed, S. I. (2020). Towards Automated Sexual Violence Report Tracking. Proceedings of the International AAAI Conference on Web and Social Media, 14(1), 250-259.