Big Data

There is not a general consensus in the literature as to how to define big data, but a common framework to describe them are the so-called three Vs or the three dimensions of big data: volume (the quantity of stored big data), variety (the variety of documents that constitute big data), and velocity (the speed at which new data is being generated). Big data are characterized by high values of all these three dimensions. A fourth dimension has been added later, veracity, which refers to the biases, noise, and abnormality in data that may make any result of their analysis completely meaningless if not properly collected and treated. Big data should be distinguished from large data sets or “lots of data” because it is not the volume of data alone that makes a set of data “big,” but their inherent complexity. The advent of big data has been hailed by some scholars as a new era for research, based on a new paradigm of science. Anyhow, another part of the scientific community expresses perplexity about the effective extent of the data revolution pointing out a number of critical points. Anyhow, without a doubt, big data analytics is a trending topic offering a large assortment of analyses designed to drive evidence-based decision-making both for the private business/industrial and the public/social sectors. Nevertheless, it raises some privacy issues that call for the definition of new de-identification techniques and procedures to guarantee the individual’s privacy.