Measuring the Diffusion of Innovations with Paragraph Vector Topic Models

David Lenz () and Peter Winker
Additional contact information
David Lenz: Justus-Liebig-University Giessen

MAGKS Papers on Economics from Philipps-Universität Marburg, Faculty of Business Administration and Economics, Department of Economics (Volkswirtschaftliche Abteilung)

Abstract: Measuring the diffusion of innovations from textual data sources besides patent data has not been studied extensively. However, early and accurate indicators of innovation and the recognition of trends in innovation are mandatory to successfully promote economic growth through technological progress via evidence-based policy making. In this study, we propose Paragraph Vector Topic Model (PVTM) and apply it on technology related news articles to analyze innovation related topics over time and gain insights regarding their diffusion process. PVTM represents documents in a semantic space, which has been shown to capture latent variables of the underlying documents, e.g. the latent topics. Clusters of documents in the semantic space can then be interpreted and transformed into meaningful topics by means of Gaussian mixture modeling. Using PVTM we identify innovation related topics from 170 thousand technology news articles published over a span of 20 years and gather insights about their diffusion state by measuring the topics importance in the corpus over time. Thereby, we find that PVTM diffusion indicators for certain topics are Granger causal to Google Trends indices with matching search terms. Further, our results suggest PVTM is well suited to discover latent topics in (technology related) news articles and that the diffusion of innovations could be assessed using topic importance measures derived from PVTM.

Keywords: Topic Model; R&D; R&I; STI; Innovation; Indicators; Text Mining; Natural Language Processing; NLP (search for similar items in EconPapers)
JEL-codes: C81 C83 O30 (search for similar items in EconPapers)
Pages: 11 pages
Date: 2018
New Economics Papers: this item is included in nep-big and nep-ino
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Forthcoming in

Downloads: (external link)
http://www.uni-marburg.de/fb02/makro/forschung/mag ... 018/15-2018_lenz.pdf First 201815 (application/pdf)

Related works:
Journal Article: Measuring the diffusion of innovations with paragraph vector topic models (2020)
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:mar:magkse:201815

Access Statistics for this paper

More papers in MAGKS Papers on Economics from Philipps-Universität Marburg, Faculty of Business Administration and Economics, Department of Economics (Volkswirtschaftliche Abteilung) Contact information at EDIRC.
Bibliographic data for series maintained by Bernd Hayo ().