Systematic reviews are a widely accepted research method. However, it is increasingly difficult to conduct them to fit with policy and practice timescales, particularly in areas which do not have well indexed, comprehensive bibliographic databases. Text mining technologies offer one possible way forward in reducing the amount of time systematic reviews take to conduct. They can facilitate the identification of relevant literature, its rapid description or categorization, and its summarization.
In this paper, we describe the application of four text mining technologies, namely, automatic term recognition, document clustering, classification and summarization, which support the identification of relevant studies in systematic reviews. The contributions of text mining technologies to improve reviewing efficiency are considered and their strengths and weaknesses explored.
We conclude that these technologies do have the potential to assist at various stages of the review process. However, they are relatively unknown in the systematic reviewing community, and substantial evaluation and methods development are required before their possible impact can be fully assessed. Copyright © 2011 John Wiley & Sons, Ltd.