Cross-Platform Violence Detection on Social Media: A Dataset and Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909636582440960 |
|---|---|
| author | Chen, Celia Beland, Scotty Burghardt, Ingo Byczek, Jill Conway, William J. Cotugno, Eric Davre, Sadaf Fletcher, Megan Gnanasekaran, Rajesh Kumar Hamilton, Kristin Harbert, Marilyn Heustis, Jordan Jha, Tanaya Klein, Emily Kramer, Hayden Leitch, Alex Perkins, Jessica Sherman, Casi Sterrn, Celia Stevens, Logan Zarrella, Rebecca Golbeck, Jennifer |
| author_facet | Chen, Celia Beland, Scotty Burghardt, Ingo Byczek, Jill Conway, William J. Cotugno, Eric Davre, Sadaf Fletcher, Megan Gnanasekaran, Rajesh Kumar Hamilton, Kristin Harbert, Marilyn Heustis, Jordan Jha, Tanaya Klein, Emily Kramer, Hayden Leitch, Alex Perkins, Jessica Sherman, Casi Sterrn, Celia Stevens, Logan Zarrella, Rebecca Golbeck, Jennifer |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03312 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cross-Platform Violence Detection on Social Media: A Dataset and Analysis Chen, Celia Beland, Scotty Burghardt, Ingo Byczek, Jill Conway, William J. Cotugno, Eric Davre, Sadaf Fletcher, Megan Gnanasekaran, Rajesh Kumar Hamilton, Kristin Harbert, Marilyn Heustis, Jordan Jha, Tanaya Klein, Emily Kramer, Hayden Leitch, Alex Perkins, Jessica Sherman, Casi Sterrn, Celia Stevens, Logan Zarrella, Rebecca Golbeck, Jennifer Computation and Language Machine Learning 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. |
| title | Cross-Platform Violence Detection on Social Media: A Dataset and Analysis |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2506.03312 |