Ryan Hubert

This course is available on the MPhil/PhD in Computational Social Science. This course is freely available as an outside option to students on other programmes where regulations permit. It does not require permission.

This course is not controlled access. If you register for a place and meet the prerequisites, if any, you are likely to be given a place

This course builds foundational fluency with digital data: what it is, how it is represented, and how it is acquired, stored, managed, and presented in social science research and data science applications. Starting from core concepts, the course progresses toward more complex data types and techniques. Students learn how data is collected through web scraping, APIs, and online databases, and how it is cleaned and manipulated across common data formats, including tabular (CSV) and hierarchical (JSON, XML, RSS) structures. Students also learn to extract and process data from less structured sources such as web pages (HTML), audio-visual content, and unstructured text. The course covers principles of data storage and security, including character encoding, encryption, and database management using relational databases (e.g. SQL). Students learn how text is processed and quantified using techniques such as tokenisation, document-feature matrices, and word embeddings. They gain experience in high-quality data visualisation and develop skills to summarise and evaluate descriptive statistics to present data effectively. Students are introduced to remote computing, including working with data from remote servers, virtual machines, and connecting to them programmatically. They learn how large language models work and how to use them as tools for working with data, from cleaning and transforming to extracting structured information from unstructured sources. Throughout, students build hands-on programming skill in R and Python, with exposure to SQL and HTML/CSS for web data extraction, and develop proficiency in version control using Git and GitHub for collaborative work and coursework submission.

15 hours of seminars and 20 hours of lectures in the Autumn Term.

This course has a reading week in Week 6 of Autumn Term.

Students will use programming techniques taught in the course for coding-based exercises focused on real-world data challenges.

Grimmer, Justin, Margaret E. Roberts, and Brandon M. Stewart. 2022.Text as Data: A New Framework for Machine Learning and the Social Sciences. Princeton University Press.

Healy, Kieran. 2019. Data Visualization: A Practical Introduction. Princeton University Press. https://socviz.co/.

Jurafsky, Daniel, and James H. Martin. 2025.Speech and Language Processing. 3rd Ed. (Draft). https://web.stanford.edu/~jurafsky/slp3/.

Munzert, Simon, Christian Rubba, Peter Meißner, and Dominic Nyhuis. 2015. Automated Data Collection with R: A Practical Guide to Web Scraping and Text Mining. Wiley.

Wickham, Hadley, Mine Çetinkaya-Rundel and Garett Grolemund. 2023. R for Data Science: Import, Tidy, Transform, Visualize, and Model Data. 2nd Ed. O’Reilly. https://r4ds.hadley.nz/.

Practical test (30%).

Practical test (70%).

Midterm in-person practical test (30%) and final in-person practical test (70%), both conducted under exam conditions.

Two in-person, computer-based assessments where students demonstrate conceptual understanding and apply programming skills learned in the course to structured, real-world tasks. Marking of these assessments will be at a level appropriate for PhD students.