Frequently Asked Questions

What kind of information does text mining make it easier to find?

Typically, text mining will help to identify relationships and patterns which exist in a large set of documents, but which are otherwise extremely difficult to discover. For example, there has been a lot of interest over the last couple of years in the problem of extracting information about binding relationships betweens proteins from the biomedical literature. The identification of a document states that there exists a binding relationship between two proteins is a typical information extraction problem involving complex natural language processing techniques. However, text mining goes one step further. Having identified a large number of binding relationships, we can then apply data mining techniques in order to discover patterns in the extracted data, which leads to the discovery of information which could not have been identified merely by reading all of the documents, even if this were possible.