10 Things we knew from open-sourced Twitter algorithm

· · 333 words · 2 minute read

Twitter revealed its algorithm to the world as open source on GitHub .

But what does it mean for you?

I spent the evening analyzing it.

Here’s what you need to know:

1. Likes, then retweets, then replies 🔗

Here’s the ranking parameters:

• Each like gets a 30x boost • Each retweet a 20x • Each reply only 1x

It’s much more impactful to earn likes and retweets than replies.

Twitter algorithm: likes, then retweets, then replies

2. Images & videos help 🔗

Both images and videos lead to a nice 2x boost.

Twitter algorithm: images and videos

Generally external links get you marked as spam.

Unless you have enough engagement.

Twitter algorithm: links hurt

4. Mutes & unfollows hurt 🔗

All of the following hurt your engagement:

• Mutes • Blocks • Unfollows • Spam reports • Abuse reports

Twitter algorithm: mutes and unfollows hurt

5. Blue extends reach 🔗

Paying the monthly fee gets you a healthy boost.

Twitter algorithm: blue gives more reach

6. Misinformation is highly down-ranked 🔗

Anything that is categorized as misinformation gets the rug pulled out from under it.

Surprisingly, so are posts about Ukraine.

Twitter algorithm: misinformation is downranked so as Ukraine Crisis topic

7. You are clustered into a group 🔗

The algorithm puts you into a grouping of similar profiles.

It uses that to extend tweet reach beyond your followers to similar people.

social circles and groups

8. Posting outside your cluster hurts 🔗

If you do “out of network” content, it’s not going to do as well.

That’s why hammering home points about your niche works.

Twitter algorithm: tweeting out of your social circle

9. Making up words or misspelling hurts 🔗

Words that are identified as “unknown language” are given 0.01, which is a huge penalty.

Anything under 1 is bad.

This is really bad.

Twitter algorithm: penalty of using unknown words

10. Followers, engagement & user data are the three data points 🔗

If you take away anything, remember this - the models take in 3 inputs:

• Likes, retweets, replies: engagement data • Mutes, unfollows, spam reports: user data • Who follows you: the follower graph

Twitter algorithm: followers, engagement and user data

I hope this helps you. You know someone will benefit from this, share it with him/her, a friend or colleage.

Share: