About

Log in?

DTU users get better search results including licensed content and discounts on order fees.

Anyone can log in and get personalized features such as favorites, tags and feeds.

Log in as DTU user Log in as non-DTU user No thanks

DTU Findit

Conference paper

From university research to innovation Detecting knowledge transfer via text mining

In Proceedings of the 21st International Conference on Science and Technology Indicators (sti 2016) — 2016
From

Department of Management Engineering, Technical University of Denmark1

Technology and Innovation Management, Department of Management Engineering, Technical University of Denmark2

Department of Applied Mathematics and Computer Science, Technical University of Denmark3

Statistics and Data Analysis, Department of Applied Mathematics and Computer Science, Technical University of Denmark4

Knowledge transfer by universities is a top priority in innovation policy and a primary purpose for public research funding, due to being an important driver of technical change and innovation. Current empirical research on the impact of university research relies mainly on formal databases and indicators such as patents, collaborative publications and license agreements, to assess the contribution to the socioeconomic surrounding of universities.

In this study, we present an extension of the current empirical framework by applying new computational methods, namely text mining and pattern recognition. Text samples for this purpose can include files containing social media contents, company websites and annual reports. The empirical focus in the present study is on the technical sciences and in particular on the case of the Technical University of Denmark (DTU).

We generated two independent text collections (corpora) to identify correlations of university publications and company webpages. One corpus representing the company sites, serving as sample of the private economy and a second corpus, providing the reference to the university research, containing relevant publications.

We associated the former with the latter to obtain insights into possible text and semantic relatedness. The text mining methods are extrapolating the correlations, semantic patterns and content comparison of the two corpora to define the document relatedness. We expect the development of a novel tool using contemporary techniques for the measurement of public research impact.

The approach aims to be applicable across universities and thus enable a more holistic comparable assessment. This rely less on formal databases, which is certainly beneficial in terms of the data reliability. We seek to provide a supplementary perspective for the detection of the dissemination of university research and hereby enable policy makers to gain additional insights of (informal) contributions of knowledge dissemination by universities.

Language: English
Year: 2016
Proceedings: 21st International Conference on Science and Technology IndicatorsScience and Technology Indicators Conference
Types: Conference paper
ORCIDs: Woltmann, Sabrina , Clemmensen, Line Katrine Harder and Alkærsig, Lars

DTU users get better search results including licensed content and discounts on order fees.

Log in as DTU user

Access

Analysis