Keyword selection and processing strategy for applying text mining to patent analysis

Previous studies have applied various methodologies to analyze patent data for technology management, given the advances in data analysis techniques available. In particular, efforts have recently been made to use text-mining (i.e. extracting keywords from patent documents) for patent analysis purposes. The results of these studies may be affected by the keywords selected from the relevant documents – but, despite its importance, the existing literature has seldom explored strategies for selecting and processing keywords from patent documents. The purpose of this research is to fill this research gap by focusing on keyword strategies for applying text-mining to patent data. Specifically, four factors are addressed; (1) which element of the patent documents to adopt for keyword selection, (2) what keyword selection methods to use, (3) how many keywords to select, and (4) how to transform the keyword selection results into an analyzable data format. An experiment based on an orthogonal array of the four factors was designed in order to identify the best strategy, in which the four factors were evaluated and compared through k-means clustering and entropy values. The research findings are expected to offer useful guidelines for how to select and process keywords for patent analysis, and so further increase the reliability and validity of research using text-mining for patent analysis. 2015 Elsevier Ltd. All rights reserved.