Introductory description

In an era of widespread digitization of data and the continuous evolution of novel computational techniques, new and exciting opportunities emerge for studying human behaviour. This module introduces students to the topic of applied behavioural data science, equipping them with skills and knowledge for gaining new insights into people’s behaviour in real-world social contexts. This module is specifically tailored for the students on the MSc in “Behavioural and Economic Science” and “Behavioural Data Science” who are interested in combining their understanding of advanced quantitative methods with the theoretical ideas about human behaviour.

Module aims

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

Introduction to Behavioural Data Science
Data Mining and Scraping
Supervised Machine Learning
Unsupervised Machine Learning
NLP: Introduction to Text Analysis
NLP: Large Language Models
Social Simulation Approaches
Agent Based Modeling
Network Analysis I
Network Analysis II

Learning outcomes

By the end of the module, students should be able to:

• Describe existing applications of computational models for studying human behaviour.
• Understand how to generate and answer new questions about people’s attitudes, beliefs, and preferences by using methodologies from computational behavioural and social science.
• Develop new analytical approaches for uncovering new insights about human behaviour with computational methods.
• Implement advanced computational methodologies to extract, process, and analyse human data.
• Design and explore simulations of human social networks.

Indicative reading list

Dehghani, M., & Boyd, R. L. (Eds.). (2022). Handbook of language analysis in psychology. The Guilford Press.
Hills, T. (2024). Network Analysis. Cambridge University Press.
Fowler, J. H., & Christakis, N., (2011). Connected: The surprising power of our social networks and how they shape our lives. Little, Brown Spark.
Jackson, Joshua Conrad, David Rand, Kevin Lewis, Michael I. Norton, and Kurt Gray. "Agent-based Modeling: A Guide for Social Psychologists." Social Psychological & Personality Science 8, no. 4 (May 2017): 387–395.

Interdisciplinary

The module concerns applications of advanced computational methods in the context of behavioural and social science research. The computational methods are primarily developed and used in statistics and computer sciences. The areas of application encompass psychological and economic aspects of human behaviour. Some broader applications of the social models will involve topics that touch on areas of political science (e.g., polarization) and public health.

Subject specific skills

At the end of the module, the student will be able to:

• Design research in the areas of computational behavioural and social science.
• Analyse large volumes of human generated data using supervised and unsupervised methods.
• Create scraping methods for harvesting online data.
• Conduct computational analysis of textual data
• Simulate social processes and analyse social networks

Transferable skills

Critical evaluation of the academic literature
Ability to design and conduct research projects
General programming and data analysis skills