The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Josef Taalbi. Photo

Josef Taalbi

Senior lecturer

Josef Taalbi. Photo

Linking innovations and patents - a machine learning assisted method

Author

  • Mathias Johansson
  • Jakob Nyqvist
  • Josef Taalbi

Summary, in English

This paper describes the methodology behind the matching of patents and a literature-based innovation output indicator (LBIO) collected from trade journals covering the manufacturing and ICT service sectors in Sweden 1970-2015. A combination of manual processing and simple machine learning tools has enabled the identification, classification and linking of patents that otherwise would have been very difficult for either of the methods to detect on its own.
Data generated using this method can be used to assess many aspects of the relationship between patenting, knowledge accumulation and innovation activity.

Department/s

  • Department of Economic History
  • Sustainability transformations over time and space
  • DigitalHistory @ Lund
  • Media History
  • Lund University Humanities Lab
  • CIRCLE
  • Research support

Publishing year

2022

Language

English

Publication/Series

SSRN:s working paper series

Document type

Preprint

Publisher

Social Science Research Network (SSRN)

Topic

  • Other Social Sciences

Keywords

  • Innovation
  • Patents
  • Machine-learning
  • LBIO

Status

Published

Project

  • SWINNO 3.0 Significant Swedish technological Innovations from 1970 until now

Research group

  • DigitalHistory @ Lund