Measuring Technological Innovation over the Long Run

By Bryan T. Kelly, Dimitris Papanikolaou, Amit Seru, Matt Taddy. 2018

355 citations recorded by the source corpus.

We use textual analysis of high-dimensional data from patent documents to create new indicators of technological innovation. We identify significant patents based on textual similarity of a given patent to previous and subsequent work: these patents are distinct from previous work but are related to subsequent innovations. Our measure of patent significance is predictive of future citations and correlates strongly with measures of market value. We identify breakthrough innovations as the most significant patents – those in the right tail of our measure – to construct indices of technological change at the aggregate, sectoral, and firm level. Our technology indices span two centuries (1840-2010) and cover innovation by private and public firms, as well as non-profit organizations and the US government. These indices capture the evolution of technological waves over a long time span and are strong predictors of productivity at the aggregate and sectoral level.

Subfields: Management of Technology and Innovation, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/17a1ce2cc90e901e4f6bbc4a7d843dca3f430828

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management of Technology and Innovation

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Exposure of occupations to technologies of the fourth industrial revolution (2021, background): “Another approach is described by Kelly et al. (2020), who describe “breakthrough patents” which significantly differ in text content from previous patents and thus might have particularly high impact.”
New Frontiers: The Origins and Content of New Work, 1940–2018 (2022, methodology): “16We also follow Kelly et al. (2020) in using data from Berkes (2018) to get citation counts for patents issued prior to 1976.”
Technology, Vintage-Specific Human Capital, and Labor Displacement: Evidence from Linking Patents with Occupations∗ (2022, methodology): “To obtain an empirical analogue to the response of labor productivity and the labor share to technology, we rely on (and extend) the analysis in Kelly et al. (2021).”
Text as Data (2017, background): “In a similar vein, Kelly et al. (2018) use cosine similarity among patent documents to create new indicators of patent quality.”