I’ve been grappling with the problem of how to find out what a group of professionals blog about. That seems simple enough on the face of it, but when there are over 9,000 blogs in a sample set of data, it’s not so easy. I can’t read every one, and even if I could, can you imagine how long it might take me to group them into topics?
Enter computer science in the form of algorithms.
I’ll gloss over the hours…. days…. weeks of researching how the various alternatives work, and why algorithm A is better than algorithm B for my type of data. Turns out k-means is the one I need.
Continue reading at: