Biggest New Approach:The platform will be evaluating not only the content of individual tweets but how the way Twitterati behave on the platform. The algorithm will be using thousands of behavioral signals like filtering search, replies, and update recommendations. If the Twitter algorithm believes that any Twitterati is trying to modify or distort the conversation and acting like a jerk; it will automatically push (lower) down the tweet at the bottom. Twitter will be able to improve the health of the conversations and experiences on Twitter by using new tools to address the conduct from ethical and behavioral perspective. It won’t be even waiting for the users to report such abuse content or potential threats to them. It’s a one step ahead action to create a user-friendly experience and maintain peace on the platform. The initiative is meant to get out ahead of problems that might normally result in an abuse report and spoils the user experience under the existing system. In testing, Twitter has said the changes led to an 8% drop in abuse reports on conversations (the discussions that happen in the replies to a tweet) and a 4% drop in abuse reports in the search. These drops, the company believes, indicate that something is working.
Behavior signals that could result in content getting demoted include:
- users who tweet at a large number of accounts they don’t follow;
- the frequency a user has been blocked by people they interact with;
- if a user (Twitterati) has created many accounts using a single IP address; and
- if an account is closely related to accounts that have violated Twitter’s terms of service.