This paper proposes technical keyword-based analysis of patents to monitor emerging technologies, and uses a keyword-based model in contents-based patent analysis. This study also presents methods to automatically select keywords and to identify the relatedness among them. After using text-mining tools and techniques to identify technical keywords, a technical keyword-context matrix is constructed. The relatedness between pairs of keywords is then identified in a transformation of this matrix. Patent documents are clustered by using a hierarchical clustering algorithm based on patent document vectors. As a result, emerging technologies can be monitored by identifying clusters composed of technical keywords. A case study of mechanisms of electron transfer in electrochemical glucose biosensors is given to demonstrate how the proposed method can monitor emerging technologies.
http://www.sciencedirect.com/science/article/pii/S0040162516302256
Author(s): Junegak Joung, Kwangsoo Kim
Organization(s): Pohang University of Science and Technology
Source: Technological Forecasting and Social Change
Year: 2016