Cross-Platform Violence Detection on Social Media: A Dataset and Analysis
By: Celia Chen , Scotty Beland , Ingo Burghardt and more
Potential Business Impact:
Helps stop online threats by teaching computers.
Violent threats remain a significant problem across social media platforms. Useful, high-quality data facilitates research into the understanding and detection of malicious content, including violence. In this paper, we introduce a cross-platform dataset of 30,000 posts hand-coded for violent threats and sub-types of violence, including political and sexual violence. To evaluate the signal present in this dataset, we perform a machine learning analysis with an existing dataset of violent comments from YouTube. We find that, despite originating from different platforms and using different coding criteria, we achieve high classification accuracy both by training on one dataset and testing on the other, and in a merged dataset condition. These results have implications for content-classification strategies and for understanding violent content across social media.
Similar Papers
Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration
Computation and Language
Finds hate speech using one smart system.
Towards High-Fidelity Synthetic Multi-platform Social Media Datasets via Large Language Models
Computation and Language
Creates fake social media posts for research.
Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches
Computation and Language
Finds and stops bad online words.