Machine Learning Meets Economic Geography: Alternative Data and Methods for Mapping and Analysing Geographies of Knowledge Production and Knowledge Relations

• Milad Abbasiharofteh – Utrecht University – m.abbasiharofteh@uu.nl
• Jan Kinne – Leibniz Centre for European Economic Research (ZEW), istari.ai UG (haftungsbeschränkt)

In economic geography, quantitative empirical studies have used mostly secondary data on patents, scientific publications, and R&D projects. These studies have contributed to the understanding of how knowledge production is geographically bounded, and of how regions, firms, and individuals create, maintain, and dissolve knowledge ties. However, more recently, scholars address the importance of using alternative data to address unresolved research questions (Duranton and Kerr, 2018; Fritsch et al., 2020).

The exponential growth of ‘big data’ coupled with enhanced computational capacity and high-performance machine learning techniques provide a range of new opportunities for mapping and analysing geography of knowledge production and knowledge relations. To name a few, this ranges from relational web data on firms in multiple countries (Abbasiharofteh et al., 2021; Kinne and Lenz, 2021) to Twitter data and news items (Ozgun and Broekel, 2021), but also digitized historical newspaper archives (Peris et al., 2021). Such data sources however require specific techniques for cleaning, manipulation, and analysis developed by the machine learning community. Whereas several scientific communities such as computational social science, networks science, and applied economics have started to take advantage of machine learning techniques (Emmert-Streib et al., 2020; Muscoloni et al., 2017; Storm et al., 2020), it seems that the economic geography community, to some extent, has not fully leverage the power of such methodological toolboxes.

We therefore invite contributions on methods of mining and analysing alternative data on geographies of knowledge production and knowledge flow. This includes, but not limited to, the following topics:

• empirical investigation of geography of knowledge production using large-scale textual data (e.g., news items and twitter data),
• mapping and analysing the rise and decline of innovative places using historic textual data (e.g., historical newspaper database),
• investigating inter-firm knowledge relations using relational web data (e.g., inter-firm hyperlink relations),
• mapping and analysing inter- and intra-firm, -city, and -regional networks using unstructured textual data,
• semantic analysis of intellectual property documents (patents and trademarks) using machine learning techniques (e.g., natural language processing techniques such as word embeddings and Transformers).

References

• Abbasiharofteh, M., Kinne, J., Krüger, M., 2021. The Strength of Weak and Strong Ties in Bridging Geographic and Cognitive Distances. ZEW Discussion Paper No. 21-049, Mannheim.
• Duranton, G., Kerr, W., 2018. The Logic of Agglomeration, in: Clark, G.L., Feldman, M.P., Gertler, M.S., Wójcik, D. (Eds), The new Oxford handbook of economic geography (First edition). Oxford University Press, Oxford, pp. 347–365.
• Emmert-Streib, F., Yang, Z., Feng, H., Tripathi, S., Dehmer, M., 2020. An Introductory Review of Deep Learning for Prediction Models With Big Data. Frontiers in Artificial Intelligence 3, 831. doi:10.3389/frai.2020.00004.
• Fritsch, M., Titze, M., Piontek, M., 2020. Identifying cooperation for innovation―a comparison of data sources. Industry & Innovation 27 (6), 630–659. doi:10.1080/13662716.2019.1650253.
• Kinne, J., Lenz, D., 2021. Predicting innovative firms using web mining and deep learning. PloS one 16 (4), e0249071. doi:10.1371/journal.pone.0249071.
• Muscoloni, A., Thomas, J.M., Ciucci, S., Bianconi, G., Cannistraci, C.V., 2017. Machine learning meets complex networks via coalescent embedding in the hyperbolic space. Nature communications 8 (1), 1615. doi:10.1038/s41467-017-01825-5.
• Ozgun, B., Broekel, T., 2021. The geography of innovation and technology news - An empirical study of the German news media. Technological Forecasting and Social Change 167 (6), 120692. doi:10.1016/j.techfore.2021.120692.
• Peris, A., Meijers, E., van Ham, M., 2021. Information diffusion between Dutch cities: Revisiting Zipf and Pred using a computational social science approach. Computers, Environment and Urban Systems 85 (4), 101565. doi:10.1016/j.compenvurbsys.2020.101565.
• Storm, H., Baylis, K., Heckelei, T., 2020. Machine learning in agricultural and applied economics. European Review of Agricultural Economics 47 (3), 849–892. doi:10.1093/erae/jbz033.