The University of Washington Tacoma is working on a tool that will seek out “hate speech” on social media.
UW Tacoma is currently working on software that will target and identify “hate speech” on social media. A press release from the university, which was first highlighted by Campus Reform, details the work being done by a team of researchers to stop “hate speech” on the Internet.
The project deploys “machine learning” to detect tweets contain words or phrases that have been deemed hateful by the researchers.
One aspect of De Cock and Nascimento’s larger research involves using machine learning to detect misogynistic tweets or those that contain hate speech directed at immigrants. “There is a lot of this material that appears in tweets or on Facebook and it’s becoming a real issue,” said De Cock. “It’s very difficult for social media companies to do proper moderation, simply because of the sheer amount of content that is published every day.”
First, the researchers provide the software with social media posts that they have deemed “hate speech.” The software analyzes these posts and searches for words and phrases the appear multiple times.
The process starts with tweets that have been marked by human annotators as misogynistic or hateful toward immigrants. “These examples are given to the computer as training examples to learn from, in a process called supervised learning,” said De Cock. “The level of additional guidance we give to the computer during the training process varies widely. You could do something called deep learning – which is very powerful – where you give very few hints and expect that the program will figure it out.”
Critics of such technology argue that innocent social media users may be accused of “hate speech” as a result of an imperfect algorithm. It is not clear at this point if social media companies are working directly with the University of Washington Tacoma’s researchers.
Stay tuned to Breitbart News for more updates on this story.