Putting the Semantic Web to work in e-Commerce with GoodRelations

Millions of us rely upon online information to inform purchasing decisions, but the ad hoc fashion in which free-text descriptions of products and services are interpreted and offered up by mainstream search engines makes this a far less accurate process than we might wish. Working quietly behind the scenes the GoodRelations vocabulary is setting out to do something about this, and with adopters such as Best Buy already onboard they're off to a great start.

Last week, I spoke with Martin Hepp of Germany's Universität der Bundeswehr München and Jamie Taylor of San Francisco startup Metaweb (best known to readers of this blog as the home of Freebase) to learn more. The result has just been released as a podcast.

Within specific organisations and supply chains, of course, Master Data Management is already well understood. Processes and procedures are in place to ensure that products are accurately and unambiguously described, and I touched on some of the semantic technology applications in this 2009 piece for Semantic Universe.

The picture becomes somewhat less clear as data moves out of the enterprise and onto the web. Even on the product website itself, much of that internal structure and richness is inadequately conveyed. For the consumer (or aggregator) wishing to compare and contrast MP3 players from a number of competing providers, it can frequently be difficult to accurately ensure that they really are comparing apples with apples. It is here that GoodRelations comes into its own, offering data providers a consistent way in which to describe key attributes of their business and its products.

Yahoo! already works to intelligently represent GoodRelations data in search results, and Martin Hepp asserts that Google "is doing something" with the data too. GoodRelations-encoded product descriptions, it seems, perform better in the mainstream search engines than their less structured competitors. The rich structure is also available for use in specific applications far beyond the generic search engine, and we touch on some of these possibilities during the conversation.

US-based consumer electronics retailer Best Buy already embeds GoodRelations RDFa in product pages, and reports improvements in findability and use.

Closer to home (for me, at least), UK supermarket giant Tesco has begun to experiment with embedding RDFa in pages. GoodRelations terms aren't used - yet - but it will be interesting to see how quickly that changes, and the applications that third parties might begin to build that leverage all this rich structure.

Have a listen to the podcast, and see what you think. Does GoodRelations have a place on your website?