Data and Network Science in the Geography of Work

• Neave O’Clery – University College London
• Balázs Lengyel – Eötvös Loránd Research Network – lengyel.balazs@krtk.mta.hu
• Samuel Heroy – University College London
• Mattie Landman – University of Oxford

In recent years exciting advancements have been made at the intersection of data science and economic geography. Data-driven ideas and methods borrowed from computer science, mathematics, physics, and computational social science have been harnessed to investigate technological change in local labor markets and provide new fertilizing potential across disciplines. Examples are wide ranging. Among others, the application of text analysis to mine datasets such as job calls, curriculum vitaes, or social media, and the deployment of sophisticated data and network analysis tools to uncover patterns of individual careers, labor flows, co-worker interactions belong to this quickly evolving interdisciplinary area. Given the ever-increasing range of new types of data exploited to better understand economic processes, and the growing interest in the field, the time is ripe to foster further innovation and exploration at this interface.

This special session aims to highlight quantitative techniques, methodological developments and applications across a range of domains related to the geography of work, including economic complexity and evolutionary economic geography, urban mobility and planning, and processes on spatial and/or social networks. In particular, we wish to feature new methodological advancements specifically developed or tailored for applications in these areas, and novel uses of existing algorithms and tools derived from machine learning and network science.

We welcome submissions on a wide range of topics within these areas. Examples include:

• Innovative data collections to test theories of economic geography
• Statistical models from network science to analyze social and collaboration networks
• Machine learning techniques such as NLP to investigate work-related communication in social media
• Causal analysis of networks and other models for processes in labor markets
• Statistical or hierarchical community detection on networks (e.g. occupation networks)
• Network based models for diversification processes in labor markets
• Network resilience models for understanding crises and technology-related changes in labor markets
• Agent-based models on social networks for knowledge diffusion
• Classification of visitation and mobility patterns to understand labor markets in cities
• Prediction of labor market progress using ML and GIS techniques
• Network models to understand segregation and inequalities in local labor markets

References

• Alshamsi, A., Pinheiro, F. L., & Hidalgo, C. A. (2018). Optimal diversification strategies in the networks of related products and of related research areas. Nature Communications, 9(1), 1-7.
• Brummitt, C. D., Gómez-Liévano, A., Hausmann, R., & Bonds, M. H. (2020). Machine-learned patterns suggest that diversification drives economic development. Journal of the Royal Society Interface, 17(162), 20190283.
• Lengyel, B., Bokányi, E., Di Clemente, R., Kertész, J., & González, M. C. (2020). The role of geography in the complex diffusion of innovations. Scientific Reports, 10(1), 1-11.
• Mealy, P., Farmer, J. D., & Teytelboym, A. (2019). Interpreting economic complexity. Science Advances, 5(1), eaau1705.
• Moro, E., Frank, M. R., Pentland, A., Rutherford, A., Cebrian, M., & Rahwan, I. (2021). Universal resilience patterns in labor markets. Nature Communications, 12(1), 1-8.
• O’Clery, N., Yıldırım, M. A., & Hausmann, R. (2021). Productive Ecosystems and the arrow of development. Nature Communications, 12(1), 1-14.
• Park, J., Wood, I. B., Jing, E., Nematzadeh, A., Ghosh, S., Conover, M. D., & Ahn, Y. Y. (2019). Global labor flow network reveals the hierarchical organization and dynamics of geo-industrial clusters. Nature Communications, 10(1), 1-10.
• Straulino, D., Landman, M. & O’Clery, N. (2021). A bi-directional approach to comparing the modular structure of networks. EPJ Data Science, 10(13).
• Tóth, G., Wachs, J., Di Clemente, R., Jakobi, Á., Ságvári, B., Kertész, J., & Lengyel, B. (2021). Inequality is rising where social network segregation interacts with urban topology. Nature Communications, 12(1), 1-9.