An algorithm developed at the Queensland University of Technology (QUT) in Australia can identify misogynistic content on Twitter with 75% accuracy.
The researchers mined a dataset of 1 million tweets, which they refined to 5,000 by searching for those containing certain abusive keywords.
Those tweets were categorized as misogynistic or not based on context and intent and input to the machine learning classifier to build its classification model.
Said QUT's Richi Nayak, "Teaching a machine to differentiate context, without the help of tone and through text alone, was key to this project's success, and we were very happy when our algorithm identified 'go back to the kitchen' as misogynistic; it demonstrated that the context learning works."
From Queensland University of Technology (Australia)
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found