摘要：Do you want to cure cancer? It doesn’t matter whether your research is about solving one of the grand challenges of humanity or addressing a more humble question – your first step is likely to be looking at what others have done before.Due to the ever-increasing number of scholarly publications (about 1.5 million new articles published every year), building up an overview of any field of study is an extremely time-consuming process.In prominent topics such as cancer research, it is even more difficult: for the last ten years alone, the UK PubMed Central (UKPMC) database lists 312,308 citations with the word ‘cancer’ in the title – browsing them at the leisurely pace of 85 per day will take you about ten years.And by that time, ten years’ worth of new articles on cancer will have appeared.To make such a search even more complex, relevant articles may not feature the keyword ‘cancer’ and critical information may be hiding in a footnote within a completely unrelated publication.There is huge potential for advancing knowledge by systematically identifying, analysing and cross-referencing existing research, but the work required is prohibitively time-consuming and expensive.Unless we use machines to help us – and that is where text mining comes into play.
