I’ve just come across yet another interesting, simple but somehow limiting definition of how collective intelligence is achieved, in the The Hype and the Hullabaloo of Web 2.0 by Ellyssa Kroski:
“Companies that adhere to Web 2.0 principles understand how to harness the collective intelligence to make their systems better. A collective intelligence is achieved when a critical mass of participation is reached within a site or system, allowing the participants to act as a filter for what is valuable. The user reviews on Amazon.com sort out the worthy resources from the inadequate. Citysearchs user-created reviews identify quality restaurants…”
It was then picked up by Five Great Ways to Harness Collective Intelligence of Dion Hinchcliffe, which lists:

1) Be The Hub of A Hard To Recreate Data Source – This is a classic Web 2.0 concept and success here often devolves to being the first entry with an above average implementation. Examples include Wikipedia, eBay, and others which are almost entirely the sum of the content their users contribute. And far from being a market short on remaining space, it’s lack of imagination that’s often the limiting factor for new players. There is so much more terrific software like digg and del.icio.us waiting to be created. So don’t wait until it’s perfect, get your collective intelligence technique out there that creates a user base virtually on its own from the innate usefulness of its data. Just be careful and avoid crowded niches, like peer production news.
2) Seek Collective Intelligence Out – This is the Google approach. There is an endless supply of existing information waiting out there on the Web to be analyzed, derived, and leveraged. In other words, you can be smart and use what already exists instead of waiting for it to be contributed. For example, Google uses hyperlink analysis to determine the relevance of a given page and builds its own database of content which it then shares through its search engine. Not only does this approach completely avoid a dependency on the ongoing kindness of strangers it also lets you build a very big content base from the outset. This ultimately has interesting intellectual property implications, as I’ve discussed before.
3) Trigger Large-Scale Network Effects – This is what Katrinalist and CivicSpace did and many others have done. This is arguably harder to do than either of the methods above but it can be great in the right circumstance. With one billion connected users on the Web, the potential network effects are theoretically almost limitless. Smaller examples can be found in things like the Million Dollar Pixel Page. That’s not to say that network effects don’t cut both ways and are probably not very repeatable, but when they happen, they can happen big.
4) Provide A Folksonomy – Self-organization by your users can be a potent force to allow the content on your site or social software to be used in a way that more befits your community. It’s the law of unintended uses again, something Web 2.0 design patterns strongly encourage. Allow users to tag the data they contribute or find and then make those tags available to others so they can discover and access things in dynamically evolving categorization schemes. Use real-time feedback to display tag clouds of the most popular tags and data; you’ll be amazed at how much better your software works. It worked for Flickr and del.icio.us and it’ll probably work for you too.
5) Create a Reverse Intelligence Filter – Like Ellyssa points out, the blogosphere is the greatest example of this and sites like Memeorandum have been using this to great effect. The idea is that hyperlinks, trackbacks, and other information references can be counted and used as a reference to determine what it’s important. Combined with temporal filters and other techniques and you can create situation awareness engines easily. It sounds similar to #2 but it’s different in that it can be used with or without external data sources and is aimed not at finding but at eliding the irrelevant altogether as an active filter.

At the end of his post, Dion promises, “I’ll continue to talk about this in future posts since effectively harnessing collective intelligence is one of the first order ideas in the Web 2.0 practice set.”
I am thrilled by the what new breakthroughs could be achieved by a systemic exploration of synergies and cross-fertilization between Web 2.0 and such “classic” CI themes as C I & All Quadrants All Levels, Co-intelligent Economy, Collaborative Taxonomy, Local to Global to Local, and Shared Attention.