Abstract
This paper compares the results from quantitative text mining to qualitative expert reviews to identify emerging technologies in the fields of solar photovoltaics (PV), wind power, ocean and tidal energy, hydropower. The text mining analysis is based on the software “Tools for Innovation Monitoring” (TIM). The TIM software extracts a set of relevant keywords from a corpus of pertinent scientific publications. TIM outputs are compared to those extracted by the software VOSviewer, showing agreement. The top 300 ranked keywords are the optimum trade-off between retrieved technologies and analyst efforts. The emerging technologies identified by the experts can be retrieved in the top 300 keywords with a probability of 65 %, 25 %, depending on the technology sector and the algorithm adopted. The more salient keywords tend to correspond to technologies with an established and univocal jargon such as: "dye sensitised solar cells" or "vertical axis wind turbines". Two methods are here used and compared: the frequency of author keywords and the term frequency-inverse document frequency (TF-IDF) algorithm. The comparison of their performances is not showing a general prevalence of one method against the other, but rather a different suitability to different technology sectors.
Highlights
The comparison exercise presented in this paper aims at providing analysts with practical insights on how to better use text mining software to identify emerging technologies
Bibliometric software with text mining features can be used by technology analysts to identify emerging and promising technologies in specific sectors, using quantitative analysis
This paper tests the use of Tools for Innovation Monitoring (TIM), a bibliometric software developed by the Joint Research Centre of the European Commission
Summary
This paper compares qualitative technology assessments performed by experts with quantitative bibliometric and text mining analysis of relevant terms. Semi-automated software findings are quantitatively compared with qualitative cognitive expert reviews by adopting specific indicators described in our previous work (Moro, Boelman, Joanny, & Garcia, 2018). This work should be considered propaedeutic to readers interested in understanding in depth our methodology. In this paper some methodological implementation is presented. Results are discussed and used to suggest methodologies and approaches to the analysts interested in technology mapping by software
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
