PeopleRank: Quora Is Developing An Algorithm To Determine And Rank User Quality

It’s no secret that Q&A site Quora is exploding in terms of usage and growth. Currently the site is getting around 164,000 unique visitors per month (December 2010 stats from comScore), and we’ve heard from a source that the service is doubling users every four months. The drawback to that kind of growth is that content could suffer in return (i.e. the Yahoo Answers issue). While Quora co-founder Charlie Cheever has alluded to some of the ways that the company is planning to mitigate this issue, he recently went into more detail about these initiatives in a new Quora post titled ‘Scaling Up.’

Cheever writes that the startup is working on several new projects to support to new users, moderate massive influxes of content and to help the site scale. One of the most interesting projects he mentioned was that the company is currently developing an algorithm to determine user quality, which will be a huge addition in terms of technology. Here’s what Cheever wrote:

We’re developing an algorithm to determine user quality. The algorithm is somewhat similar to PageRank but since people are different from pages on the web and the signals that are available on Quora are different from those on the web, it’s not exactly the same problem. We’ll use this to help decide what to show in feeds, when to send notifications, and how to rank answers.

While a huge endeavor in terms of development,it makes total sense for Quora develop a PageRank-like technology to rank people and content on the site. For those of you who don’t know this, PageRank is the link analysis algorithm was developed by Google co-founders Larry Page and Sergey Brin that is the technological foundation for Google Search.

Cheever says that the startup is also working to get more people to help evaluate the quality of new content on the site, effectively crowdsourcing moderation on Quora. He adds: Most of the people who use Quora have pretty good judgement, and we believe there is some wisdom in crowds. Preliminarily, this approach is very promising.

And education is another key part of helping Quora scale, says Cheever. He asserts if new users understand what Quora is when the join, that will help influence users to add appropriate content to the site. For example, Quora has added a brief tutorial quiz before new users add new questions and Cheever says that it has made a big difference in reducing the number of questions that don’t meet guidelines or policies.

He adds that Quora is working a number of other ways to improve the site and mitigate growth.

If Quora is able to develop a ‘PeopleRank’ algorithm that works and can scale, this could no doubt be a very important piece of technology generally. And a patented algorithm will certainly make the startup even more of a desirable acquisition target.

Hat tip to Shervin Pishevar for coining PeopleRank.