Meta Stack Exchange is where users like you discuss bugs, features, and support issues that affect the software powering all 157 Stack Exchange communities.

What is meta?
Here's how it works:
  1. Any Stack Exchange user can ask a question
  2. The community provides support, votes on ideas, and reports bugs
  3. Your voice helps shape the way Stack Exchange operates

I'd like to generate a Data Explorer query which makes a reasonable ranking of users by the average quality of their answers.

Reputation is heavily influenced by quantity. As Jeff points out, quantity is essential — but even in his story, quantity was a means to an end; the end being quality.

Other than having a large enough sample size (50-100 questions minimum for a user to be included), I'd like to get a basic idea of reputation excluding the quantity factor.

What factors, and potentially algorithm, are good indicators of total average quality?

My rough, first ideas:

  • Median answer score
  • Top answer percentage
  • Accepted answer percentage
share|improve this question
I suspect that the biggest complicating factor you'll meet is the different activity levels in various tags. – dmckee Apr 15 '11 at 20:23

Well there's definitely a "quality" algorithm in use on Stack Exchange sites already, aswe already have a tool to be able to review "low quality posts" and they have an associated quality score. Perhaps without giving up too much of the secret sauce, they could expound upon it?

edit: Related - Heuristics for detecting a bad answer

Though it's not just that "not bad" answers are good, there are other qualities that make an answer good that aren't just the inverse of qualities that make an answer bad.

share|improve this answer
It's not just 10k (, but I would guess that "quality score" is only calibrated for the low end of the spectrum (it mostly picks up short answers). – NickC Apr 15 '11 at 20:27
Indeed, like @Renesis says, the heuristics are only shown for low quality posts. – Arjan Apr 15 '11 at 20:34
@arjan but in this case "low quality" and "short length" are the same. The heuristic doesn't even attempt to classify posts > (n) chars. – Jeff Atwood Apr 16 '11 at 0:00

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .