We’ve heard questions from some of you relating to our work to drive healthy conversation on Twitter. People are asking us 1) about the breadth and precision of our work & 2) the impact of our work on the Search experience. We wanted to address these questions transparently here.
In May, we started using behavioral signals and machine learning to reduce people’s ability to detract from healthy public conversation on Twitter. This approach looks at account behavior & interactions with other accounts that violate our rules.
On 1) We’re always working to improve our behavior-based ranking models - their breadth and accuracy will improve over time. It’s important to note that these behavior signals are not binary, and they are one of many other signals that factor into ranking.
To be clear, our behavioral ranking doesn’t make judgements based on political views or the substance of tweets. We recently publicly testified to Congress on this topic judiciary.house.gov/wp-content/upl…
On 2) Some accounts weren’t being auto-suggested even when people were searching for their specific name. Our usage of the behavior signals within search was causing this to happen & making search results seem inaccurate. We’re making a change today that will improve this.
We believe this work is really important to creating a healthier Twitter and we want to continue improving. Your feedback helps us do that so please keep it coming.
