ABSTRACT
Accurate prediction of disease spread and the infection rate can help the spread rate by taking precautionary measures. However, big data is required and there are various challenges of data processing. The challenges of big data are discussed in this chapter. Before starting with any kind of analysis, data pre-processing is a very important task. Data collection from various sources is the first task of data pre-processing. In this chapter various data sources of COVID-19 data are discussed. Data collected from these sources needs to undergo data cleaning before data analytics; in this chapter, the data cleaning process is explained in detail. The concluding part of the chapter deals with the knowledge extraction strategies used for different types of data. As data exists as text files, image files, audio files, and video files, the extraction method applied to each of the data source will be unique.
