Text Data Mining also known as Text Mining is a computer process to analyze large amounts of unstructured textual documents in search of word patterns and relationships. For researchers, the impact of text data mining can be the identification and discovery of new insights and unobserved themes.  Many of the Library's databases offer datasets that permit text data mining.  Two of the most popular source of ready to use datasets for text mining are found within TDM Studio and the Gale's Digital Scholar Lab.  

Government published information and some journals from commerical publishers are also available for text mining.