Social Networks in Economic Geography and Spatial Machine Learning 2400-ZEWW951

The main aim of the course is to make students familiar with the broad variety of data science methods for spatial data – the analysis of spatial networks and spatial machine learning. Course is divided into two parts. The first one will be conducted by a visiting scholar: prof Balázs Lengyel and the other will be conducted by prof. Katarzyna Kopczewska and mgr Maria Kubara.

The course will be coordinated by an onsite lecturer – mgr Maria Kubara, while the whole class material will be delivered by the visiting professor.

The course will be taught in an intensive workshop setting over the course of two weeks between 17 and 28 February 2025. The students are asked to bring their own laptops with R v.3.3.0+ and RStudio Desktop installed in order to take active part in the practical live code exercises discussed during the class.

(tylko po angielsku)
The main aim of the course is to make students familiar with the broad variety of data science methods for spatial data – the analysis of spatial networks and spatial machine learning. Course is divided into two parts. The first one will be conducted by a visiting scholar: prof Balázs Lengyel and the other will be conducted by prof. Katarzyna Kopczewska and mgr Maria Kubara.

The course will be coordinated by an onsite lecturer – mgr Maria Kubara, while the whole class material will be delivered by the visiting professor.

The course will be taught in an intensive workshop setting over the course of two weeks between 17 and 28 February 2025. The students are asked to bring their own laptops with R v.3.3.0+ and RStudio Desktop installed in order to take active part in the practical live code exercises discussed during the class.

---------
The first part of the course:
(17-19 February, classes with the visiting scholar)

Instructor:
Prof Balázs Lengyel –
ANETI Lab, Institute of Economics, HUN-REN Centre for Economic and Regional Studies and Corvinus Institute of Advanced Studies
Institute for Data Analytics and Information Systems, Corvinus University of Budapest

Aims and objectives and description of the course:
The course aims to cover introduction to network science, network science methods, and recent research in spatial social networks and their impact on economic and technological progress. Students will learn R programming tools to work with network data, visualize networks and analyze them.

Learning outcomes:
The completion of the course will enable to reach the following outcomes:
• Learn basic concepts and techniques of applied network science.
• Learn theory and concepts of social networks, and their relevance to economic outcomes.
• Learn about the recent research on social networks in cities and regions.
• Acquire skills in R programming and software tools to work with networks.
• Learn statistical methods to analyze networks and networked phenomena.
• Familiarize with agent-based modeling of spatial diffusion on networks.

Course description
The 2025 February sessions of the Social Networks in Economic Geography course deal with empirical approaches on spatial social networks and on economic and technological processes. The course includes lectures and discussion with students. The lectures will incorporate on how spatial social networks are described by quantitative tools, how the dynamics of social networks in space can be quantified and modelled, how these are related to economic- and technological progress and innovation diffusion. The coursework will focus on reading the given material and practicing the coding examples.

Schedule of the course:

17.02.2025 morning session:
Network science introduction
• Definitions
• Network models
• Node and network characteristics
• Community detection
Reading:
Barabási 2017
Mandatory Chapters: 2, 9
Optional Chapters that we will talk about: 3, 4, 5

17.02.2025 evening session:
Social networks in geographical space
• Costs and benefits of ties
• Distance effect
• Spatial modularity
• Individual outcomes of spatial networks
Reading:
Borgatti et al. 2009,
Lengyel et al. 2015

18.02.2025 morning session:
Networks of innovation and regional development
• Brokers in networks
• Brokerage and atypical innovations
• Co-worker networks and agglomeration externalities
• Productivity growth
Reading:
Abbasiharofteh et al 2023,
Burt 2004,
Eriksson and Lengyel 2019,

18.02.2025 evening session:
Networks in cities
• Urban mobility networks
• Network fragmentation and inequalities
Reading:
Tóth et al. 2019
Pintér and Lengyel, 2024
Bokányi et al. 2021

19.02.2025 morning session:
Spatial diffusion through networks
• Innovation diffusion
• Complex contagion vs virus spreading
• Bass ABM
Reading:
Lengyel et al. 2018,
Brockman and Helbing 2013

Methodology to be used:
Students must read the papers for each class that we will discuss. Then, every class will provide a short tutorial in R coding to deal with the research problem in question.

Compulsory reading:
- Abbasiharofteh, M., Kogler, D.F., Lengyel, B. (2023) Atypical combination of technologies in regional co-inventor networks. Research Policy.
- Burt, R (2004) Structural holes and good ideas. American Journal of Sociology 110 (2) https://doi.org/10.1086/421787
- Borgatti, S. P., Mehra, A., Brass, D. J., & Labianca, G. (2009). Network analysis in the social sciences. Science, 323(5916), 892-895.
- Brockmann, D., & Helbing, D. (2013). The hidden geometry of complex, network-driven contagion phenomena. Science, 342(6164), 1337-1342.
- Eriksson, R. H., & Lengyel, B. (2019). Co-worker networks and agglomeration externalities. Economic Geography, 95(1), 65-89.
- Glückler, J. (2007). Economic geography and the evolution of networks. Journal of Economic Geography, 7(5), 619-634.
- Juhász, S., & Lengyel, B. (2018). Creation and persistence of ties in cluster knowledge networks. Journal of Economic Geography, 18(6), 1203-1226.
- 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, 15065 (2020)
- Lengyel, B., Varga, A., Ságvári, B., Jakobi, Á., & Kertész, J. (2015). Geographies of an online social network. PloS ONE, 10(9).
- 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, 1143 (2021).

Recommended readings:

Barabási, A-L (2017) Network Science. http://networksciencebook.com

---------
The second part of the course:
(20, 21, 26, 28 February)

Instructors:
dr hab. Katarzyna Kopczewska prof. ucz.
mgr Maria Kubara

This part of the course will focus on machine learning techniques application to spatial data. The topics include:
• Spatial machine learning – challenges and opportunities
• Spatial data clustering – techniques and applications
• Geographically Weighted Regression and Spatial Random Forest
• Spatial artificial neural networks
• Recurrent neural networks in spatial setting
The list may be extended, depending on the initial skills and the interest of the group.

---
Both parts of the course will be complementary and will provide the students with a broad overview of the spatial network analysis and spatial machine learning techniques and their applications in R.