The GroupSwim Diving Board

We met up with one of our customers last night to compare notes on semantic technology. This was a great case of two companies trying to accomplish similar goals (making sense of unstructured data) in different ways. They heavily use statistical analysis on massive data sets. By importing and analyzing the data, they can draw mathematical relationships between words, documents and document sets and then use crazy smart algorithms to make sense of them. Their ultimate goal is to make these massive data sets manageable and discover relevant content. We take another approach and use natural language processing to analyze the data our customers put into their sites. Our datasets tend to be much smaller but are high quality since someone doesn’t add something to GroupSwim unless they want to share it. Then, we compare the language used in the content to other semantic sources including WordNet, Wikipedia, etc. to do our automatic tagging and analysis. Our ultimate goal is to make it easy for people to add content and then for others to find it through meaningful semantic relationships and search.

The exercise of comparing the two methods and seeing the high level similarities was fun. We also brainstormed different ways they could use GroupSwim since they are a great customer. I was definitely the least intellectual person in the room, but it was something to behold when our CTO and their scientist guy started throwing around terms like the semantic web, divisive clustering, agglomerative clustering, and a bunch of other stuff I can’t pronounce.