Enhancing Detection of Relationship Abuse in Text with Multi-Task Learning (Student Abstract)
Abstract
Intimate Partner Violence is a global, life-threatening public health issue that can be prevented by recognizing emotionally aggressive behaviors that signal the potential for future relationship abuse. To help identify these precursory unhealthy behaviors, this study proposes a Multi-task Learning framework for training robust models capable of detecting not only physically abusive behaviors but also emotionally abusive behaviors, such as belittling or manipulation, which historically precede physical abuse. Preliminary results indicate that Multi-task Learning can improve detection of emotional abuse and help tune detection models to particular kinds of relationship abuse.
Cite
Text
Rinks. "Enhancing Detection of Relationship Abuse in Text with Multi-Task Learning (Student Abstract)." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35294Markdown
[Rinks. "Enhancing Detection of Relationship Abuse in Text with Multi-Task Learning (Student Abstract)." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/rinks2025aaai-enhancing/) doi:10.1609/AAAI.V39I28.35294BibTeX
@inproceedings{rinks2025aaai-enhancing,
title = {{Enhancing Detection of Relationship Abuse in Text with Multi-Task Learning (Student Abstract)}},
author = {Rinks, Caroline},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {29477-29479},
doi = {10.1609/AAAI.V39I28.35294},
url = {https://mlanthology.org/aaai/2025/rinks2025aaai-enhancing/}
}