Topics: Introductions and course overview. What is Computational Social Science? Good computing practices.

SLIDES (.pdf): Introduction to the course.

Background reading

Topics: Computational social science: research opportunities and challenges. Overview of theories, methods, and data. Ethics of social science research in the digital age. Big data, big bias? Data collection: automated data collection from the web.

SLIDES (.pdf): Computational Social Science - Research opportunities and challenges.

Background reading

Readings for discussion

Topics: Survey research in the digital age. New sampling techniques. Multilevel regression and poststratification.

Readings for discussion

Topics: Large-scale online experiments. Basics of UNIX. Parallel programming with R.

SLIDES (.pdf): Experimental research in the digital age.

Background reading

Readings for discussion

Topics: Introduction to automated text analysis. Sources of textual data. String manipulation in R. Regular expressions. Text processing with quanteda. Dictionary methods.

SLIDES (.pdf): Introduction to automated text analysis. Dictionary methods applied to sentiment analysis.

Background reading

Readings for discussion

Topics: supervised machine learning applied to text classification. Crowd-sourcing the creation of training datasets.

SLIDES (.pdf): Introduction to supervised learning applied to text classification.

Background reading

Readings for discussion

Topics: Unsupervised machine learning (topic models).

SLIDES (.pdf): Introduction to unsupervised machine learning. Topic models.

Background reading

Readings for discussion

Topics: Ideological scaling of documents. Event detection. Introduction to word embeddings.

SLIDES (.pdf): Advanced automated text analysis.

Background reading

Readings for discussion

Topics: Basic concepts in social network analysis. Types of random networks. Strong and weak ties. Network visualization.

SLIDES (.pdf): Introduction to social network analysis.

Background reading

  • Sinclair, B. (2016). Network Structure and Social Outcomes: Network Analysis for Social Science, in Alvarez, M. (ed.) Computational Social Science. Cambridge: Cambridge University Press. [Full text available through USC libraries]

  • Chapters 1, 2, and 3 in Easley, D., & Kleinberg, J. (2010). Networks, crowds, and markets. Cambridge University Press.

Readings for discussion

Topics: Social contagion processes: homophily vs influence. Collecting social media data.

Background reading

Readings for discussion

Topics: Latent variable models, with applications to networks. Introduction to exponential random graph models.

SLIDES (.pdf): Latent space network models. Community detection.

Background reading

Readings for discussion

Topics: Spatial data. Geographical Information Systems (GIS). Spatial autocorrelation. Spatial autoregresion models.

SLIDES (.pdf): GIS.

Background reading

Readings for discussion

Topics: Deep learning. Images, audio, and video as data.

Background reading

  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.

Readings for discussion

Student presentations of research projects.

Student presentations of research projects. Course recap.