Jove
Visualize
Contact Us

Related Experiment Video

Updated: Nov 10, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K

Predicting innovative firms using web mining and deep learning.

Jan Kinne1,2,3, David Lenz3,4

  • 1Department of Economics of Innovation and Industrial Dynamics, ZEW Centre for European Economic Research, Mannheim, Germany.

Plos One
|April 1, 2021
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Innovation in hyperlink and social media networks: Comparing connection strategies of innovative companies in hyperlink and social media networks.

PloS one·2023
Same author

Greenwashing in the US metal industry? A novel approach combining SO<sub>2</sub> concentrations from satellite data, a plant-level firm database and web text mining.

The Science of the total environment·2022
Same author

An integrated data framework for policy guidance during the coronavirus pandemic: Towards real-time decision support for economic policymakers.

PloS one·2022
Same author

Measuring the diffusion of innovations with paragraph vector topic models.

PloS one·2020
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

This study introduces a novel method for generating web-based innovation indicators to support science, technology, and innovation (STI) policy. The approach efficiently identifies product innovator firms, offering a cost-effective alternative to traditional metrics.

Area of Science:

  • Economics of Innovation
  • Science, Technology, and Innovation (STI) Policy
  • Data Science and Machine Learning

Background:

  • Effective STI policy making relies on accurate innovation indicators for economic growth.
  • Traditional indicators (patents, surveys) suffer from limitations in coverage, timeliness, granularity, and cost.
  • Existing indicators fail to provide a comprehensive view of the innovation system for policymakers and researchers.

Purpose of the Study:

  • To propose and develop a novel approach for generating web-based innovation indicators.
  • To create a scalable and cost-efficient method for identifying product innovator firms.
  • To overcome the limitations of traditional innovation metrics.

Main Methods:

  • Utilized the German Community Innovation Survey for labeled firm data (product innovator/no product innovator).

Related Experiment Videos

Last Updated: Nov 10, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K
  • Developed an artificial neural network classification model trained on web text data of surveyed firms.
  • Applied the trained model to a large dataset of German firms' web texts to predict product innovator status.

    • Main Results:

    • The web-based approach successfully identified product innovator firms at a large scale and low cost.
    • Predictions demonstrated reliability when compared against patent statistics, survey benchmarks, and regional indicators.
    • The method offers significant potential for enhanced coverage and regional granularity in innovation metrics.

    Conclusions:

    • The proposed web-based indicator generation method is a valuable and cost-efficient addition to existing innovation metrics.
    • This approach addresses shortcomings of traditional indicators, particularly in terms of coverage, timeliness, and cost.
    • The findings support the use of web data and machine learning for more comprehensive STI policy support.