Kindle, Google and the significance of context in understanding (historical) meaning

An interesting post by Jim Stogdill on the Radar O'reilly blog highlights the current limitations of the Google age (wondrous as it is). He started thinking about the implications of the Bezos comment from the Kindle announcement, “Our vision is every book, ever printed, in any language, all available in less than 60 seconds.”

"The problem is that old books reference people and other stuff that a contemporary reader would have known immediately, but that are a mystery to me today - a mystery that needs solving if I want to understand what the author is trying to say, and to get that sense of how they saw the world. If you want to see what I mean, try reading Winston Churchill's Second World War series."

Even going forward in a digitized world this problem remains. What precisely is the meaning? – without it being filtered and recast by well-meaning Wikipedia editors. Ultimately, time as a dimension is important to meaning. Time, meaning, and by definition context, constantly change. Even efforts to hyperlink usage and meaning in digital need to address this element, otherwise the problem persists of needing to go to the research library to get unvarnished understanding of the author’s contemporary meaning.

Recommendation engines need context and personalization

A post from ReadWriteWeb about recommendation engines featuring Baynote, a software as a service company that helps sites target their recommendations, covered some interesting ground. Baynote argues recommendations based on current context produces superior results than those based on historical actions. The post cites Amazon as the leader for the opposing approach of recommendations based on historical views and transactions. Since I've had “bubble bath” recommended to me by Amazon, I understand historical data can lead to offers wide of the mark. (I’d made a 1-time purchase of Soap products as a gift for my mother).

The ideal employs both methods. An understanding of historical patterns and current context and intent will deliver more precise recommendations than either method. To return to my bubble bath example, for 330 days of the year showing me bubble bath is ridiculous. But, approximately one year after my original purchase and knowing it shipped to someone else, an offer of bubble bath related items might work.

Going forward a broader definition of user context than Baynote offers will improve recommendation engines. Context seems to be limited by onsite behavior. Other inputs like current real world activity, location, and friends interests all improve the results. Read Write Web astutely points out that room exists for multiple approaches in the marketplace.