Using Social Network Analysis to Understand Data

Lecturer: Thomas Hills

Modality: In presence

Week 1: 10-14 August 2026

 

Workshop Contents and Objectives

Social network analysis is used to understand communities by investigating their structure. The same principles can be used to study other kinds of data in industry, economics, communication, informatics, and business. Network analysis allows us to identify structure in our data, including key actors, hierarchies of relationships, brokers, groups and local communities, patterns of information flow, and the resilience of the community.

Networks are made up nodes connected by edges.   Any data in a matrix format can be represented as a network.  In social network analysis, the nodes are usually people. But nodes can be used to represent almost anything, such as cities, brands, online communities, scientific articles, political organizations, colors in paintings, emotions, historical events, or words in a language. This means that network analysis can be used to unlock and understand almost any kind of data.

In this workshop, students will learn the basic concepts of social network analysis and extend its use to network analysis more broadly, including data analysis and network visualization. Students will learn the material in a practical hands-on fashion, largely using R, and all the code will be provided. In previous years, students with limited knowledge of R have made great progress.

By the end of the workshop, students will have a vocabulary for understanding network analysis and should have the knowledge needed to understand most of the research in network analysis that they are likely to see in the social sciences. If students have ongoing projects of their own, they will be able to investigate these and gain new insights into their own research.

In addition to learning how to make networks from data, students will learn concepts like small world analysis (how structured is the network?), homophily (do similar nodes cluster together?), network closure (are nodes in the network in harmony with one another?), distance (how far away are objects in the network from one another?), clustering and community detection (what are the communities in my data?), and centrality (are some nodes more important than others?).

 

Workshop design

The course will alternate between lectures and interactive programming using pre-written code in R.

 

Detailed lecture plan (daily schedule)

Day 1: Intro to network analysis, making and representing networks

Day 2: Measuring things using networks

Day 3: Generating networks, null hypotheses

Day 4: Models and processes on networks

Day 5: Advanced topics and short presentations from students

 

Class materials

All materials will be provided online.

 

Prerequisites

Students taking this workshop should have some experience with R and RStudio. There are free or inexpensive online courses well worth the investment in time (e.g., Datacamp) that offer introductory courses in R that are sufficient prerequisites for this course. A general introductory book to statistics in R will also work (e.g., Dalgaard, P. 2008. Introductory statistics with R is where I started). Though the course will primarily use R, I will provide all the code. This course can be a way to improve your R skills as well.

 

Recommended readings or preliminary material

What our participants appreciated most

"Thomas is a very inspiring researcher in the way that he sees scientific publications as "starting a debate" and, while doing thorough research, not worrying too much about if everything that is published is really "true". For me, that was a new perspective taking my fear from making mistakes and just start doing. He has a very engaging way of teaching, interest for his students and their problem as well as a broad knowledge which he shares in a followable, practical, respectful, relaxed, funny way. The workshop surpassed my expectations. | most enjoyed the topic, practical appraoch of the workshop, the class atmosphere and some alternative general approachesto issues (role of researchers, AI, ...)."

"The mix between theory and hands-on practice in R was particularly well balanced."

Thomas Hills

University of Warwick

Thomas Hills is Professor of Psychology at the University of Warwick, concentrating on how humans represent and navigate information in the mind and society, including topics such as conspiracy beliefs, aging memory, and cultural evolution. He directs the Behavioral and Data Science MSc and has held fellowships with the Alan Turing Institute and the Royal Society. His publications include work in psychology, communications, education, and economics, and focus on issues associated with large-scale analysis of data.

Read