In recent years, the social media has become a powerful tool for sharing people thoughts and feelings. As a result data is being generated, analyzed and used with a tremendous growth rate. The data generated by numerous updates, comments, news, opinions and product reviews in social websites is very useful for getting insights. As there are multiple sources, the size, speed and formats of the gathered data affects the overall quality of information. To achieve quality information, preprocessing step is very important and decides future roadmap for efficient big data analysis approach. In context to social big data we are addressing the preprocessing phase which includes cleaning of data, identifying noise, data normalization, data transformation, handling missing values and data integration. In this paper we have proposed a new approach polymorphic SBD (Social Big Data) preprocessor which provides efficient results with multiple social big data sets. Also available data preprocessing methods for big data are presented in this paper. After efficient and successful data preprocessing steps, the output data set will be efficient, well formed and suitable source for any big data analysis approach to be applied afterwards. The paper also presents an example case and evaluates min-max normalization, z-score normalization and data mapping for the case presented.
POLYMORPHIC SBD PREPROCESSOR: A PREPROCESSING APPROACH FOR SOCIAL BIG DATA