The SGD and Pegasos classifiers would be ideal for this. The features should include the poster as well as the content. Geo and date might be useful.
On Thu, Jan 21, 2010 at 11:42 AM, Jason Rutherglen < [email protected]> wrote: > Not sure if a Tweet could fall under multiple categories. We'd > want to allow multiple classification systems, I'm thinking here > of the Stanford log-linear classifier, among others. If this > worked I'd personally want to start using it to because CL is > too painful. > -- Ted Dunning, CTO DeepDyve
