Published Paper Details:

Mankind have witnessed an unbelievable growth of the importance of social media in last few years. When it all started tweets, facebook messages, youtube videos, social tagging, blogs writing systems, etc. served more-less just as a source of entertainment of a few enthusiastic users. Today the time has changed, news spreading over social media may be considered as the most important changes of our society, Mostly the Bad news. Also advertisements and news about new services, products related to the services and companies launching the products, these are spreading very quickly through the means of social media. This is indeed a great possibility for promoting new products and services. But, according to sociological studies, negative opinions and news spread much quicker than positive news, therefore, if negative news appears on social platform about a particular organization, it must react quickly, in order to avoid losses. Due to such large amount of documents appearing every second in social media platforms, analyzing all these documents by human experts is nearly impossible, hence there is a Colossal need for the automatic breakdown of such documents. For the analysis of the documents, we have to consider some special properties of the application domain Into account. In particular, the uncontrolled, dynamic and rapidly-changing Content of social media documents This study demonstrates how Machine Learning with Data Mining techniques can address the aforementioned challenges. In this paper, we focus on the analytic components that allow to predict the number of feedbacks that a document is expected to receive in the next 24 hours.