Introduction to Machine Learning for the Social Sciences

Copenhagen Centre for Social Data Science

Dates and time:
27-29 August 2024 from 9 am to 4 pm.

This course will introduce the basics of big data and machine learning and how it can be used in the context of social science research. No prior knowledge is assumed, and it is well-suited for people with no prior experience using big data or machine learning. The course will cover different topics including how big data methods differ from inferential statistics, data cleaning and pre-processing, different machine learning models and explainable AI methods, data ethics and privacy, as well as bias and responsible AI.

Core machine learning principles such as cross-validation, out-of-sample prediction, and hyper-parameter tuning will be introduced. A key focus will be on interpretable machine learning models such as regression-based models, decision trees, and random forests.       

The assessment will involve completing a machine learning analysis, either in Python or in R. Therefore, some prior experience with one of these coding languages is preferred. A basic understanding of inferential statistics is also preferred. Participants can bring their own data or use the data that will be provided. 

Academic Aim:
– To think critically about when Big Data and machine learning should be used for social science research (assess advantages, disadvantages, and limitations)
– To be able to perform a machine learning analysis

Target group: Social science background. To gain most from the course some prior experience with R or Python and a basic understanding of inferential statistics is ideal.

Course organiser: Rosa Ellen Lavelle-Hill, Assistant Professor, Department of Psychology, University of Copenhagen

Disclaimer:
DDSA has explicit permission from Arcanic and the owners of the https://phdcourses.dk/ website to display the courses on ddsa.dk.