We’ve seen the story pop up a lot in national headlines lately. Social media companies are trying to figure how to deal with hate speech, and as these platforms get bigger, managing hateful language on them is only going to get harder. While companies are trying to figure this out, a new tool is monitoring how users engaging in hate speech on Twitter are behaving.
The tool, Exploring Online Hate, looks at the activity of 1,000 Twitter accounts and tracks which topics are being discussed and which hashtags are being used by the accounts. It also looks at which links are being shared by those users.
The creators of the project started with 40 of what they call “seed accounts” that use hate speech on a regular basis. From there, they were able to use Twitter’s API to put together of list of followers for each of the initial accounts. Here’s a little more from the creators about the specifics of their methodology:
“Through a combination of algorithmic methods involving statistical feature selection in combination with human curation, we generated a list of the top accounts engaging in hateful conduct amongst these follower accounts. “
A little complicated, yes. But tools like these can be very useful in figuring out exactly how hate speech spreads on social platforms.
While the creators are tracking these accounts, they will not, however, be releasing the names of the users they’re studying. Colin Lecher from The Verge has more on this:
“The online hate dashboard, maybe necessarily, also keeps its list of accounts secret, making independent examination impossible. Publicizing the list, its creators explain, could lead to changes in the listed users’ behavior.”
The tool was created by The New America Foundation and the Anti-Defamation League. The groups say they’ll be publishing quarterly reports on their findings.