In the post I covered how the algo update now counts follower to following ratios in their scoring and some other cool stuff. I also made a recommendation for the next update: “My recommendation for the next algo update? Figure out a way to incorporate user interaction (@’s, retweets, replys) After all, it’s all about the conversation ;)”
Later that night, I received yet another comment from Dharmesh Shah, the developer behind the Twitter Grader algo. He said:
Thanks for the second round of thoughtful analysis.
The algorithm was indeed updated this weekend (and I think it’s “better”).
Quick note: We have 200,000+ unique profiles that have been graded. In a way, this is good, but the flip side is that it takes some time to “normalize” the database of grades. We’ve got significant server resources powering the software, but I tend to “trickle-in” the recalculations. That’s a long-winded way of saying: It’s going to take some time for the actual grades to completely reflect the updated algorithm.
Making progress (I think). The point about tracking retweets and the “quality” of conversations for a given user profile is a really good one. I’ve been thinking about that one and will try to incorporate something like this in a future update.
Well, it looks like the future update came sooner than expected! 2 days is a pretty good turn-around time if you ask me! Today, lots of users are noticing a boost in their Twitter grade because of what I believe to be an incorporation into the algo of user-interaction.
Here are a few things to look at:
Just for good measure, here are the charts, even though they are of less significance this round..
And the Previous Chart:
Now, take a look at martinbowling, katemorris, and neoblog. All of these users saw somewhat significant jumps in their grades, without significant increases in followers or other activity in updates or following numbers over the past 2 days.
All of these users have a high volume of incoming @‘s, part of the user-interaction recommendation that Dharmesh said would be incorporated!
But there’s more.. I also checked @garyvee’s score, who I have been monitoring over the past few months. He has 18,352 followers, follows 2,134, and 3,306 updates. The past couple months his score has varied from 99.9 to 100.1. But is notorious for not replying to incoming @‘s that he receives. Today, after the update, his score is down to a 99.7. Consistent with this trend is @chriswinfield, who also saw a slight drop in score today. Chris and I actually know each other apart from twitter, and he’s a great guy.. But, he gets a TON of @‘s because of all of the twitter polls and questions that he does, but doesn’t @ back at nearly the volume that he gets them in. (sorry chris ;))
This leads me to believe that Twitter Grader has incorporated in an update to their algorithm that accounts for incoming and outgoing @‘s on your twitter account, like I had mentioned in my last post.
If you find this to be true, leave a comment so I can check out your profile! And remember tweeps, its all about the conversation!