A study on cognitive social data fusion

Abstract

Traditional data mining usually deals with data from a single domain. In the big data era, we are facing a diversity of datasets from different sources in different domains. These datasets consist of multiple modalities, each of which has a different representation, distribution, scale and density. Big data have volumes in range Exabyte's ten to the power of eighteen. A large number of data's are stored in Big Data storage every second. For instance in YouTube for every second a video of size 72 hours are being uploaded. It shows that big data have a big scope in handling of large data. Big data for learning, intelligence, data fusion, social network, mining and so many plays a vital role in it. The big data technologies along with machine learning algorithm have developed lots of advanced development in the field of social mining, network and social Medias. It has also developed so many challenges in data storage, handling, representation, mining, analysing the user behaviours and so many. In Social mining along with text the symbols are also analysed for effective mining of users. This paper does not only introduce high-level principles of each category of methods, but also give examples in which these techniques are used to handle real big data problems. The data storage size can be optimized by using the map reduce algorithm in a effective way for data storage in big data. When the repeateddata's are replaced with its reference then the storage will be optimized. Thus this method implementation will leads to the effective data mining and the analysing of persons behaviour more effectively.