Mining Social Media Data: Discovering Contradictedness Quantities

Social networks produce enormous amount of data every single minute. In numbers, each day 55 million status are updated in Facebook and 500 million tweets are sent. More than 30 billion pieces of content are shared on Facebook every month. Identifying the significance of this vast quantity of data presents challenges for data mining and sentiments analysis scientists. Very little work has been carried out in the field of mining Social Media Data in order to determine the important and the significance of a Facebook post, twitter tweet or YouTube link, subjectively. It is quite easy to identify the importance of social media quantities using statistics tools such as number of likes of a Facebook post or a Twitter's tweet but it is really hard to identify the significance of these quantities subjectively i.e the ability to determine the significance of social media quantities based on the impact of those quantities on human being or the incitement caused in different fields and the proper utilization of newly discovered knowledge caused by certain social media quantities. In this paper, we identify the significance/importance of social posts subjectively using sentiment analysis techniques and we propose a new subjective measure of social media data significance we call Contradictedness measure.