Introduction to Cultural Analytics

The course is targeted towards PhD students in the humanities and social sciences who do not yet possess specific computational or technical skills, but who are interested to learn more for their future thesis work. Apart from some of the guest lectures, the course will be physical and take place at campus Engelska Parken, Uppsala University.

The course is module based, which means that you are free to choose how many modules you would like to take. Each module equals 1.5 ECTS, or 2 weeks at 50 %. Modules 1–2 are mandatory, while modules 3–6 are optional. To make the course equal 7.5 ECTS you thus take module 1–2 plus an additional three modules. For details on each module, please see the plan below.

Main course goals

The aim of the course is to introduce methods for computational text analysis from a humanities and social sciences perspective. This covers and pays equal attention to providing:

knowledge about computational text analysis methods and their relevance for humanities and social sciences tasks
knowledge about machine learning and its basic concepts, as well as such methods’ possibilities and limitations
practical skills to employ computational methods for text analysis by using existing software, and by following and adapting basic programming scripts
the ability to critically reflect upon the results derived from computational methods (regarding ethical, statistical, and empirical/material-oriented concerns)
the ability to highlight epistemological concerns regarding computational and statistical methods from a humanities and social sciences perspective

Pedagogical basis

The general idea of the course is to combine practical hands-on tasks on technical (and statistical) methods with critical discussion and reflection on methodological concerns, limitations, and biases. Each module will typically consist of an introductory lecture, a discussion text seminar, and a practical lab. In some modules there will also be guest lectures by a leading expert. The hope is that the components feed into each other in the way that theory and reflection become concretised by practical work, and that practical work becomes meaningful and more critically aware through reflexive seminars, etc.

Examination

The course is examined: 1) through active participation in labs, seminars, and lectures; 2) through completion of lab assignments for each module; and 3) through a written final essay.

Course program

Module 1: Introduction to Cultural Analytics and Python
Module 2: Data curation and analysis
Module 3: Data collection (web scraping, APIs, social media)
Module 4: Natural language processing (NLP)
Module 5: Computational text analysis
Module 6: Applied machine learning (ML)

Final essay

A written case study that relates to the students’ PhD projects, where some cultural analytics method(s) introduced in the course are used to pose and answer a humanities or social sciences research question. The requested length of the essay will reflect the number of modules taken.