Patent text similarity and cross-cultural venture-backed innovation

F. Trevor Rogers

Journal of Behavioral and Experimental Finance, 2020, vol. 26, issue C

Abstract: Portfolio companies with cross-cultural venture-backing that produce patents which are textually more similar to industry peers also produce more patents and higher quality patents. 4.9 million cosine similarity measures between the patents of 958 venture-backed portfolio companies from 28 different nations provide results that are able to generalize beyond the English language with the addition of a cultural-linguistic distance measure. Latent Dirichlet allocation topic modeling applied to the patent text validates these categories, making these results robust against deviation between industries. The results provide a textual measure that venture capital firms from all nations can use to determine if the patents produced by their portfolio companies are the type that encourage greater innovation.

Keywords: Venture capital; Corporate innovation; Patents (search for similar items in EconPapers)
JEL-codes: F21 G24 G40 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S2214635019302059

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:beexfi:v:26:y:2020:i:c:s2214635019302059

DOI: 10.1016/j.jbef.2020.100319

Access Statistics for this article

Journal of Behavioral and Experimental Finance is currently edited by Michael Dowling and Jürgen Huber

More articles in Journal of Behavioral and Experimental Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().