Unsupervised social media events clustering using user-centric parallel split-n-merge algorithms

Social Networks have been developed dramatically just in decades. People now have a convenient way to interact with both social media and other people by making the most of using these social networks. Nevertheless, there is still lack of useful tools that can help users (both consumers and providers) managing such social media under events perspective. In order to meet one of these emerging requirements, a user-centric parallel split-n-merge framework applied for un-supervised clustering social media events is introduced. The purpose of this framework is to cluster social media to events they depict by exploiting and exploring the role of users (who) and the way users interact with data (where, what, when) and others (what, who). The output of the proposed framework can be used for event organization/summarization, and as pre-processing stage for event detection and tracking. Major advantages of the proposed framework are (1) low computational solution w.r.t large-scale data, (2) parallel running, and (3) unsupervised clustering with no training data and third-party information requirements. The comparison between the proposed framework and up-to-date methods with MediaEval2013¹ test-bed and evaluation tools shows a very competitive result.