Twitter continues to clean up its feed. The microblogging site is now targeting disruptive users, i.e. those who excessively post content that could be considered spam or a nuisance to others.
Often such users aren’t being reported for the content they post, however, they can have a negative impact on other users by consistently posting irrelevant content.
A new Twitter algorithm will be filtering such conversations to feature them less prominently in feeds. If a user happens to be interested in viewing the content, they can choose to ‘show more replies’ or see more of the post.
The newly installed algorithm detects trolls by using behavioural cues. These show when an account takes on the characteristics of a typical troll. For example, trolls tend to not confirm their email address, often sign up for more than one account, and excessively tweet or mention other Twitter accounts.
Additionally, Twitter will be monitoring the connections of such accounts with others.
According to the company, such tweet behaviours also violate its policies. However, the tweets themselves do not infringe on its policies, which means the company will be filtering it instead of deleting the user accounts.
According to initial tests, Twitter noted that there had been 4% fewer abuse reports from search and 8% fewer abuse reports from conversations. s fewer people are seeing disruptive tweets, they have fewer reasons to report them to Twitter.
“Our work is far from done. This is only one part of our work to improve the health of the conversation and to make everyone’s Twitter experience better,” explained Del Harvey, Vice President of trust and safety at Twitter. “We’re encouraged by the results we’ve seen so far, but also recognize that this is just one step on a much longer journey to improve the overall health of our service and your experience on it.”