Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Abstract
Abusive language is a massive problem in online social platforms. Existing abusive language detection techniques are particularly ill-suited to comments containing heterogeneous abusive language patterns, i.e., both abusive and non-abusive parts. This is due in part to the lack of datasets that explicitly annotate heterogeneity in abusive language. We tackle this challenge by providing an annotated dataset of abusive language in over 11,000 comments from YouTube. We account for heterogeneity in this dataset by separately annotating both the comment as a whole and the individual sentences that comprise each comment. We then propose an algorithm that uses a supervised attention mechanism to detect and categorize abusive content using multi-task learning. We empirically demonstrate the challenges of using traditional techniques on heterogeneous content and the comparative gains in performance of the proposed approach over state-of-the-art methods.
Cite
Text
Gong et al. "Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I17.17738Markdown
[Gong et al. "Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/gong2021aaai-abusive/) doi:10.1609/AAAI.V35I17.17738BibTeX
@inproceedings{gong2021aaai-abusive,
title = {{Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention}},
author = {Gong, Hongyu and Valido, Alberto and Ingram, Katherine M. and Fanti, Giulia and Bhat, Suma and Espelage, Dorothy L.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {14804-14812},
doi = {10.1609/AAAI.V35I17.17738},
url = {https://mlanthology.org/aaai/2021/gong2021aaai-abusive/}
}