Saturday, April 26, 2008

Ofamind and Twine

I was flattered to learn about the other day. Twine is the long-simmering product of Radar Networks and is remarkably similar to Ofamind in many ways. A bit of digging shows that they used Wikipedia as a basis for their tagging engine. Some reviews have been positive while others less so.

Still, I consider it a vindication of sorts, though I think they will have a hard road business-wise if they believe has a massive audience appeal. I will just mention that I interviewed with a startup called Backflip in 2000 that went nowhere as well. The business proposition for these kinds of technologies is when they provide real business value to specific knowledge worker communities--when they serve vertical domains to address specific problems.

A minor footnote: I chatted with Radar Network's Nova Spivak several times about collaboration several years back and suspect that there was a bit of, ehhhh, influence of Ofamind on Twine's development (based also on watching my weblogs). I'm just amused that I beat them to the plate with one consultant and three other ongoing engagements simultaneously. Are there diminishing returns beyond a few agile minds in what Bessemer VCs refer to as our new capital efficient web marketplace?

Thursday, April 24, 2008

Folksontamasticons and Ambiguity

Folks might not be all bad, though. For instance, in my Ofamind technology, this blog and social bookmarking sites like, the tags that are attached to documents serve to help people find and retrieve information. Tagging is a counterpoint to the idea of structured ontologies and metadata because it builds from the ground up rather than from the top down. The term coined for these tagging schemes is “folksonomy.”

But are folksonomies useful and consistent? Some studies suggest they are useful under some circumstances. For instance, querying across the titles and descriptions using tag keywords on bookmarks results in a precision-recall of only 50%. In other words, the tags are not also in the texts around 50% of the time, and so provide an additional channel of information for retrieval. People appear to think differently about tags than they do about titles and descriptions.

In terms of consistency, however, a very large number of tags are used only once or are used in differing and inconsistent ways that indicate ambiguity over multiple user subcommunities. Examples might be “architecture” used to refer to computer architecture and building design, or “camp” referring to drama or outdoor recreation.

A couple of interesting questions emerge about how to refine the power of folksonomies.

For instance, can the title and description (or full blog content) be used to automatically suggest tags that are based on other tagging schemes? The Ofamind system partially does this by automatically categorizing web content among your “views” or collections as you surf. It does a fair job, too, for a great deal of content. This can be seen as a personalized metadata tagging filter, since the view association to content is essentially a categorical tag.

Similarly, business taxonomies, controlled vocabularies, full ontologies and other mechanisms could be used at authoring time to try to suggest or overlay more consistent tags onto web content, enhancing searchability and even supporting reasoning about content. For Ofamind, a subproblem that we are currently working on is how to disambiguate extracted people, places and organizations in order to produce high-quality metadata using a combination of human tagging and automatic methods.

Then the folksonomy becomes more of a folksontamasticon, combining folksonomy, ontology and onamasticon in a rare new tag.

Thursday, April 3, 2008

Folk and Psychology

Is the reach of reason limited by our nature? That question came to me during a rather disagreeable conversation recently. The woman I was conversing with spoke almost entirely in vignettes built around folk sociology and psychology.

“Girls always grow up to marry someone like their father.” “You just don’t understand what it’s like to grow up as a redhead.” “My father hates me because I had medical problems as a child.”

Now, I try to be sympathetic of even bad self-analysis insofar as I only have to encounter it in small doses. What good can come from challenging people under those circumstances? But I increasingly wondered as the conversation continued whether there are limits to our natural capacity to overcome the patterns of folk psychology we use to attach meaning and explanation to our lives. I tried lightly challenging one of the statements and suggested that there was little or no evidence to support a given claim. Her response was that she just gave me evidence—a single example. There was some hemming and hawing about how she acknowledged that that wasn’t scientific evidence, but it was enough for her.

Isabel Allende was recently interviewed and she confessed that her entire writing method and inspiration emerged from trying to construct narratives and folk psychologies to explain her characters. Everything had an explanation and there was little difference for her between magical, religious and everyday occurrences—they all had elaborate explanatory narratives that involved mystical forces, and frameworks for punishment, reward and retribution. Magical Realist at core, but also reflecting the need for fiction to tie together into a structural form that is without the weak sense of doubt that pervades our everyday lives; people are complex and do things for complex and sometimes unexplainable reasons best regarded as tendencies.

But is there any sense in which people can change their cognitive styles? Somewhat, I think, but there are also other factors like dopamine and it’s relationship to magical thinking that are likely more resistant to active attempts at change. Still, the goal of liberal education has always had at its core the notion of refining the mind to enhance our ability to think and process information. It’s the best tool we have.