Efficient Event Detection for the Blogosphere

In this paper we come up with a novel approach for the early detection of events in blog entries. The detection of trend is already discussed pretty often. Nevertheless, in our understanding the detection of events goes one step further. The presented algorithms detects unique happenings at a given point in time by perceiving unusual frequent occurrences of words or word groups. We introduce an implementation of our algorithm, making use of the SAP HANA database in order to achieve high performance and the ability to answer live queries for events.