Abstract

Conducting literature reviews is a fundamental step in the production of science and innovation. In Physical and Technical Sciences, as well as in Life Sciences, new publications appear at exponential rates, which makes it difficult to keep up with the latest developments. In the medical field, systematic literature reviews typically start from thousands of papers on average. A strict and tedious process of paper screening ensues to guarantee full transparancy and reproducibility.
The talk will explain how a combination of data visualization, pattern mining and natural language processing can support the exploratory analysis of large collections of textual documents. We will give a short demo of Papyrus, a tool actively developed at LIST for this purpose. The talk will also discuss the usefulness of this approach for the anaylsis of other types of unstructured data sets, beyond text.