Evidence based technology and innovation policy making: An application for robotic technologies

Date

2024-7

Author

Özbay, Oğuz

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

155
views

229
downloads

Cite This

This thesis presents a framework aimed at reducing the reliance on experts in the traditionally expert-dominated foresight process by leveraging advanced methodologies to extract key insights within the field of robotics. By employing Structural Topic Modeling (STM) on an extensive collection of scientific publications and patents, the research reveals the current landscape and anticipates future trends in robotics technology. Advanced text mining techniques, such as the Naive Bayes classifier, ensure comprehensive inclusion of robotics-related publications, enhancing the accuracy of the analysis. A custom word embedding, specifically trained for robotics, facilitates the recognition of overlapping themes between academic research and industrial innovation, identifying intersections between theoretical research and practical applications. The integration of topic trends from STM with the semantic analysis of cited references within scholarly publication highlights novel developments, leading to informed and actionable policy recommendations. This study demonstrates the practical application of text mining and natural language processing in guiding policy formulation. By utilizing these advanced methods and extensive data, the framework aims to diminish the dominant role of experts, making the foresight process more data-driven and accessible. This approach underscores the importance of these tools in identifying, understanding, and steering technological advancements toward desired objectives.

Subject Keywords

Structural Topic Modeling, Word Embedding, Text Mining, Emerging Technology in Robotics, Technology Foresight

URI

https://hdl.handle.net/11511/110088

Collections

Graduate School of Social Sciences, Thesis