The abundance of textual data in modern times provides a rich source of information on social and political behavior. As a result, social scientists have increasingly turned to computational or computer-assisted methods to extract insights from this data. This course is designed to equip you with the foundational knowledge and skills required to manage and analyse textual data using R.

Upon completion of the course, you will:

• develop a conceptual understanding of basic approaches to natural language processing;
• gain familiarity with common quantitative text analysis techniques used in political science literature and be able to interpret the results; and
• learn how to implement the most widely used methods employed by social scientists.

The course covers the following topics:

• The fundamentals of quantitative text analysis using machine learning.
• Estimation of dictionary, sentiment, topic, and scaling models.
• Methods for text classification using supervised machine learning.
• Word embeddings and textual representation models.

All formal sessions will be held daily Monday-Friday 01-05 June 2026 followed by 3 weeks of self-study to complete the final assignment.

Discounted fee of £550 available to academic, non-profit and government organisations only. Enter discount code MC40-F143EA33EDC9 at checkout. Fee is £750 for all other participants.