Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Monday 5 – Friday 9 August
09:00–10:30 and 11:00–12:30
The aim of this course is to give scalable computational tools to researchers interested in investigating social network research questions.
The course will introduce R (via R notebooks) as a key tool to analyse networks:
We will discuss centralities, community detection, blockmodelling, brokerage, rewiring-based null models, and multiplex networks. I will provide datasets from diverse research projects: collaboration and communication networks, world trade, animal social networks.
ECTS credits for this course and below, tasks for additional credits:
1 additional credit Submit a 2,000–3,000-word take-home paper, testing a network hypothesis with data, with a visualisation of the network, and a statistical test of the hypothesis. Datasets and possible research questions will be made available in the course.
2 additional credits As above, plus complete two assignments, handing in one-page outputs for each.
Balázs Vedres' research furthers the agenda of understanding historical dynamics in network systems, combining insights from network science, historical sociology, and studies of complex systems in physics and biology.
His contribution is to combine historical sensitivities to patterns of processes in time with a network analytic sensitivity to patterns of connectedness cross-sectionally. A key element of this work was the adoption of optimal matching sequence analysis to historical network data.
Balázs' research has been published in top journals of sociology, with two recent articles in the American Journal of Sociology exploring the notion of structural folds: creative tensions in intersecting yet cognitively diverse cohesive communities. His recent research follows video game developers and jazz musicians as they weave collaborative networks through their projects and recording sessions.
He is the recipient of several awards and prizes, and is the founder and director of CEU's Center for Network Science.
Social network analysis benefits greatly from computational tools, and the R statistical language is a suitable environment to describe, visualise, and analyse network datasets of various sizes.
Intensive learning across disciplines is happening in social network analysis and network science. This course makes new ideas from many disciplines – statistical physics, ecology, computer science – available to the social scientist, through libraries in R, and via the interactive possibilities of R notebooks available in R studio. We will use libraries such as network, sna and igraph.
The course is a good choice for those who have not taken the first-week course Social Networks: Theoretically Informed Analysis with UCINET, because we will briefly revisit the main concepts covered there. In this case, having an awareness of the basic concepts of social network analysis would be a plus.
The course is also a good choice for those who did take first-week UCINET course, because it adds scalability of the R framework not present in UCINET to analyse larger networks, many networks, or fork the analytic strategy to various alternative methods and indices. The course also adds multiple approaches to hypothesis testing and comparisons to random baseline null hypotheses, sophisticated visualisations, and a broader range of algorithm choice. We add outlook to methods from network science not present in UCINET (such as the replication of the Watts-Strogatz small world rewiring experiment).
Day 1
We introduce R and programming basics, data import, and network descriptives. We discuss object types and programming constructs relevant to network analysis. We explore various ways to import data to R, and learn about the generation of random graphs with diverse methods. We learn about various data structures – sociomatrices, edgelists, nodelists – and ways to transform data among these formats. We will import data from various sources – Excel sheets, CSV and other delimited text formats, UCINET and other special data formats.
Day 2
We learn what makes social networks distinctive: a strong tendency to closure and positive degree correlation (assortativity). We will compare human social networks to animal social networks (and to decidedly not social network systems) to test the idea that animal social networks are indeed social. We will discuss various centrality measures, and centralisation at the graph level. We will compare centrality measures, and discuss the theoretical imagery behind these measures, with detailed explanation of the formulas for the various indices.
Day 3
We introduce measures for brokerage (structural autonomy), and various brokerage roles at the boundaries of groups. We use rewirings to generate the random baseline expectation for the relative frequency of brokerage roles, and diagnose an organisational network of a thousand workers to detect bottlenecks in information flow in between divisions.
Day 4
We look at blocklmodelling and cohesive community detection, with an emphasis on goodness of fit measures, and comparisons with random baselines. We will compare several methods of community detection, and discuss underlying assumptions about the nature of network data and processes of tie formation.
Day 5
Dedicated to advanced visualisations of network data. We discuss layout algorithms, and parameter choices for these – for small and large graphs. We also introduce node density heat maps for extremely large graphs. We learn to convey information on graphs using node size and colour, edge size and colour. We discuss graph creation and export for various purposes: research article, PowerPoint, poster, interactive online presentation.
Essential Basic knowledge of statistics and probability (probability density functions, tests of statistical significance, ordinary least squares estimator), and of data entry and manipulation (using Excel sheets, CSV, TXT data formats).
Advantageous, but not essential Basic knowledge of R (objects, vectors, matrices) and awareness of basic concepts in programming (for and while loops, if-else conditional statements).
These basics will be covered briefly, to the extent that enables independent learning.
Each course includes pre-course assignments, including readings and pre-recorded videos, as well as daily live lectures totalling at least two hours. The instructor will conduct live Q&A sessions and offer designated office hours for one-to-one consultations.
Please check your course format before registering.
Live classes will be held daily for two hours on a video meeting platform, allowing you to interact with both the instructor and other participants in real-time. To avoid online fatigue, the course employs a pedagogy that includes small-group work, short and focused tasks, as well as troubleshooting exercises that utilise a variety of online applications to facilitate collaboration and engagement with the course content.
In-person courses will consist of daily three-hour classroom sessions, featuring a range of interactive in-class activities including short lectures, peer feedback, group exercises, and presentations.
This course description may be subject to subsequent adaptations (e.g. taking into account new developments in the field, participant demands, group size, etc.). Registered participants will be informed at the time of change.
By registering for this course, you confirm that you possess the knowledge required to follow it. The instructor will not teach these prerequisite items. If in doubt, please contact us before registering.
Day | Topic | Details |
---|---|---|
Monday | R basics, network data import and descriptives |
R intro, data formats, basic network descriptives, basic graph drawing, random graphs. |
Tuesday | Strong and weak ties, assortativity, centralities and centralisations |
What makes social networks distinctive? Testing Granovetter’s strong ties hypothesis and Newman’s positive degree correlation hypothesis with human, animal social networks, and not social networks. Centrality measures and graph centralisations. |
Wednesday | Brokerage and rewiring-based statistical testing |
Brokerage measures and brokerage roles. Statistical testing for network data using random rewirings as null model. |
Thursday | Community detection and blockmodelling |
Methods to identify communities, equivalent blocks; methods to test the goodness of fit of cohesive or equivalent blockings. Comparison of disjunct and overlapping community partitions. |
Friday | In-depth network visualisation |
Graph layout algorithms and their parameters, scalability by graph size, information conveyed by node and edge attributes. Visualising for article, presentation, poster, or online. Density heatmaps. |
Day | Readings |
---|---|
Monday |
César A. Hidalgo (2016) |
Tuesday |
Mark S. Granovetter (1973) M. E. J. Newman and Juyong Park (2003) |
Wednesday |
Burt, Ronald S. 1995 Roger V. Gould and Roberto M. Fernandez (1989) |
Thursday |
James Moody and Douglas R. White (2003) |
Friday |
No readings |
We will use R studio which includes R. Use the newest version.
Please bring your own laptop. Windows, Mac, Linux.
Information on requirements from the Rstudio support pages
Useful handbook Wasserman, Stanley, and Katherine Faust (1994): Social Network Analysis. Cambridge University Press: Cambridge
More about R Torgo, Luis (2011): Data Mining with R. Chapman & Hall
Summer School
Social Networks: Theoretically Informed Analysis with UCINET