Information extraction from social media: Clustering and labelling microblogs

In today's world, social media becomes one of the most popular and fastest information bearing services. The leading social media like Twitter and Facebook produce a huge volume of information through its microblogs. The number of microblogs produced in every minute by these services is so large that the old information use to be buried under the streaming information. Moreover, sometimes the messages of these services are not organized, complete, structured and relevant to the exact topic for which it becomes difficult for the users to find the exact information they are searching for. So in this paper, we have proposed a framework to organize the microblogs in clusters and give each cluster a meaningful label. The difficulty in clustering and labelling microblogs is that they are very shortand sometimes even incomplete for what it is not easy to understand the actual meaning of the message. The traditional text mining methods fail to establish the semantic relationship between the words. In this paper, we have used a better way to cluster and label the terms having high semantic association.