Network structural analysis of technology: a study from patent perspective

Abstract

Purpose

The purpose of this paper is to analyze the network structure of technology in and between different fields, as well as the evolution of their relations.

Design/methodology/approach

Using the patent data in Derwent Innovation Index (DII) from 1991 to 2010, this paper analyzes the co-classification of Derwent Manual Code (DMC) of patents in all technology fields. Large-scaled co-classification matrices are employed to generate the DMC co-classification networks. In addition, analyses are pursued at different levels of aggregation in four five-year windows: 1991-1995, 1996-2000, 2001-2005 and 2006-2010. Using Girvan-Newman algorithm in the clustering process, the structure transformations over time are detected.

Findings

The paper identifies the key technological knowledge in certain fields and finds out how different technological fields are connected and integrated. What is more, the dynamic evolution between networks in different time periods reveals the trend of generic technology development in the macroscopic level.

Originality/value

The paper investigates a large quantity of data – all the patent data in DII from 1991 to 2010 in this paper. The paper applies Girvan-Newman algorithm in the co-classification analysis and uses co-classification networks to reveal technology network structures. Evolution coincident with the realistic technological shifts can be observed.

Citation

Xu, S., Wang, X., Liu, Z. and Luan, C. (2013), "Network structural analysis of technology: a study from patent perspective", Journal of Science and Technology Policy in China, Vol. 4 No. 3, pp. 214-235. https://doi.org/10.1108/JSTPC-01-2013-0001