The growth of Open Access has increased the pool of digital information that is available for Text Mining. This relatively new interdisciplinary field emerged in the 1980s and combines techniques from linguistics, computer science and statistics to build tools that can efficiently retrieve, extract and analyze information from digital text.
PLOS has actively promoted the field of text mining by publishing reviews, opinions, tutorials and dozens of primary research articles in PLOS Biology, PLOS Computational Biology and PLOS ONE. Furthermore, PLOS is one of few publishers who enable and encourage text mining research by providing an open API to mine our journal content.
In order to raise the profile of this field and PLOS’ contribution to it, we’re delighted to announce the PLOS Text Mining Collection, which gathers together key works published by PLOS in the field of TextMining, including three new research articles published today in PLOS ONE.
Whilst the promise of Text Mining is yet to be fully realized, a world in which all scientific literature is Open Access, allowing Text Mining tools to fully compare and contrast that data, now seems possible. Text mining has the potential to make new discoveries and open up new fields of research, but will always be dependent on the literature that is available. As part of our mission to lead a transformation in research communication, we’re delighted to showcase the research from this field and encourage debate within the community and beyond.