Twitter Said to Work on Anti-Harassment Keyword Filtering Toolby
Abuse has led to departure of several high-profile users
New solution is similar to Instagram’s keyword-based filter
Twitter Inc. is working on a keyword-based tool that will let people filter the posts they see, giving users a more effective way to block out harassing and offensive tweets, according to people familiar with the matter.
The San Francisco-based company has been discussing how to implement the tool for about a year as it seeks to stem abuse on the site, said the people, who asked not to be identified because the initiative isn’t public. By using keywords, users could block swear words or racial slurs, for example, to screen out offenders.
Twitter has struggled to find a technological solution to the turmoil that can result from the product’s core feature: anyone can publicly say anything to anyone else. Abuse has led to many high-profile departures of celebrities and journalists, who say they can no longer stand to be attacked. There was a New York Times reporter who quit after enduring a spate of anti-Semitic tweets, for example, as well as an actress Leslie Jones, who faced a similar barrage of racist and sexist attacks.
Twitter needs to attract and retain users as the growth in their numbers slows. The company has spent the past few months consulting with an outside council of anti-harassment groups about its strategy for addressing the issue, which has become one of Chief Executive Officer Jack Dorsey’s top priorities. Twitter took some small steps this year, such as making it easier for people to report abuse by letting them identify multiple offending tweets while filing their complaints. But the keyword tool, if implemented, would be the first to give users more control over what they see instead of blocking individual users after they attack.
The filtering tool could eventually become a moderator for any kind of content, the people said. For example, users could block a hashtag about an event they don’t care to read about.
Identifying keywords would be similar to the comment moderation tool recently adopted by Facebook Inc.’s Instagram app for business users. Celebrities put it to work immediately, with model Chrissy Teigen tweeting that she was blocking certain words, such as "whore" or "slut." Still, trolls could attempt to outsmart the filter by deliberately misspelling words or coming up with new ways to deliver their insults.
A spokesman for Twitter declined to comment, although the company has said it soon plans to release more substantial updates about its plans to combat harassment.