Peerworks blog

Welcome to Peerworks

Peerworks is an open source project that is building content classification tools to help online browsing, collaboration, and social discovery. We're on track to have a basic automated content classification (tagging) mechanism in early 2007, using more or less "cookbook" naive bayes methods. Beyond that we see lots of interesting extensions and problems that can only be tackled with far more statistical modeling expertise than we have. Conversely, we expect the system as it gets deployed to produce a great deal of user tagging data for various content. So we'd also like to work with statistical research projects that can use that data. Of course this raises privacy issues, but we will try to deploy the system under terms that will give researchers access to as much data as possible.

We're seeking part time or full time contractors to build statistical modeling components for an online content filtering service. We are funded by a foundation and can pay competitive consulting rates. As a distributed, web coordinated development team, we have no geographical constraints and already have a non-US developer. Since we're developing open source software, developers who work for us will be able to use the code we create in other environments. Please read our job description.

Our first project: collaborative moderation and tagging

We have chosen to work first on collaborative moderation and tagging. This has shown itself to be a very powerful set of ideas, but even users of sites that depend heavily on collaborative moderation, such as Slashdot, are relatively unsatisfied with the current state of the art. We have some ideas that we think can help such sites work significantly better. Detailed discussion of collaborative moderation.

Project updates:
Peerworks' tagging project updates can be found in the Peerworks blog. Read the latest update on the status of our tagging project, along with detailed information about our project's goals and plans.

Making society smarter through online collaboration

As organizations get larger they tend to get stupider. Luckily there are exceptions, and by studying these we can guess what it would take to live in a world of smarter institutions. One practical way to improve matters is to improve collaboration between "many small pieces loosely joined" (David Weinberger's very helpful phrase). The cheapest and most powerful way to do this is by improving online collaboration. Detailed discussion of online collaboration.

Online content production

One of the most important domains for online collaboration is online content production. This includes such activities as creating open source software, open source information resources like Wikipedia, distributed proofreading, etc. Reflection on our collective experience with this domain helps us to see some of the ways that online collaboration has worked especially well, and some of the ways that it still has problems. This experience is currently one of our major guides in choosing how to focus our efforts. —Detailed discussion of online content production.

 


Peerworks is a nonprofit effort, funded by The Kaphan Foundation. Project management and much of the design is provided by Mindloom.
Early investigation of this approach was done by Pliant Research, and is discussed in this interview.