Twitter responded to a tweet from President Donald Trump in which he accused the social network of “shadow banning” prominent Republicans.
General counsel Vijaya Gadde and head of product Kayvon Beykpour denied Trump’s claims in a blog post, saying Twitter does not shadow ban and explaining the events of earlier this week that led to the president’s tweet.
They said Twitter identified and resolved an issue in which some accounts were not appearing in search auto-suggestions, even when people were searching by the specific name of the account holders, adding that only search auto-suggestions were impacted, and the accounts, their tweets and conversations about those accounts were still surfacing in search results.
They added that “hundreds of thousands” of accounts were impacted by the issue, and it was not limited to political affiliation, as accounts of Democratic politicians were affected, as well.
As for why Republicans seemed to be affected more, they wrote, “For the most part, we believe the issue had more to do with how other people were interacting with these representatives’ accounts than the accounts themselves. There are communities that try to boost each other’s presence on the platform through coordinated engagement. We believe these types of actors engaged with the representatives’ accounts—the impact of this coordinated behavior, in combination with our implementation of search auto-suggestions, caused the representatives’ accounts to not show up in auto-suggestions. In addition to fixing search, we’re continuing to improve our system so that it can better detect these situations and correct for them.”
Gadde and Beykpour also shed some light on the process Twitter uses to rank tweets, saying as an example that if a search result contains 30,000 tweets, the social network takes these factors into consideration:
- Tweets from people you’re interested in should be ranked highly.
- Tweets that are popular are likely to be interesting and should be higher ranked.
- Tweets from bad-faith actors who intend to manipulate or divide the conversation should be ranked lower.
Signals Twitter uses to determine bad-faith actors include:
- Specific account properties that indicate authenticity (e.g. whether you have a confirmed email address, how recently your account was created, whether you uploaded a profile image, etc.).
- What actions you take on Twitter (e.g. who you follow, who you retweet, etc.).
- How other accounts interact with you (e.g. who mutes you, who follows you, who retweets you, who blocks you, etc.).
They concluded, “We’re focused on making these systems better and smarter over time and sharing our work and progress with all of you. We think it’s critical to promoting healthy public conversation on Twitter and earning trust.”