The aim of this study is detecting events on social media with improving current solutions by means of accuracy and time performance. An event is something that occurs in a short duration of time in a certain place. In this thesis, the problem is modelled as a streaming transaction process. Three different event detection method is adapted to our solution. First one is keyword-based event detection method that looks for bursty keywords in a period of time. The second one is clustering-based event detection method which is a basically an version of hierarchical clustering algorithm. And the last one is hybrid event detection method of keyword-based and clustering-based algorithms. To specify the problem as streaming transaction process, all algorithms are implemented on top of S-Store. S-Store is a streaming OLTP engine having distributed, scalable and guaranteed ordered delivery features. All of event detection methods are run and evaluated their performance with a real data set obtained from Twitter.