Menu
Menu
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Member rate 2,713.79 zł
Non-Member rate 5,427.58 zł
Save 221.03 zł Loyalty discount applied automatically*
Save 5% on each additional course booked
* If you attended a qualifying previous Methods School in 2025 or 2026, you qualify for 221.03 zł off your course fee.
Online: 3 – 4 September
Jagiellonian University: 8 – 11 September
This course introduces computational methods for analysing visual and multimodal data in social science research. It is designed for PhD students and early‑career researchers across disciplines – including political science, sociology, communication, and public policy – who work with image‑rich digital data. Basic familiarity with Python or R is assumed.
Key topics include automated image classification, unsupervised visual analysis, object and face detection, and multimodal approaches that combine images with text, including CLIP‑style models and larger vision–language models (VLMs). Methods are grounded throughout in real datasets and linked to substantive research questions across the social sciences.
The course combines pre‑recorded introductory videos and readings with hands‑on coding exercises across online and in‑person sessions. A project thread runs through the full course, ending in a short presentation. You may also submit a post‑course written analysis for an additional ECTS credit.
3 ECTS credits awarded for engaging fully in class activities.
1 additional ECTS credit awarded for completing a post-course assignment.
This course explores computational visual and multimodal analysis as a set of tools for social science research. It brings together methods from computer vision and natural language processing to address questions about how images and visual communication function in digital environments. The course is designed for researchers across disciplines – including political science, sociology, communication, and public policy – who encounter image‑rich data in their work. Basic familiarity with Python or R is assumed.
You will engage with the full range of core methods: supervised image classification using pre‑trained and fine‑tuned models, unsupervised approaches including clustering and embedding‑based methods, and object and face detection as applied examples. The course extends into multimodal analysis, reflecting the reality that visual content rarely appears in isolation. You will work hands-on with CLIP‑style vision–language models and be introduced conceptually to larger VLMs such as GPT‑4V, with attention to how these tools are being applied in current social science research.
A central focus of the course is connecting methods to research design. From the first session, you are encouraged to identify a research question and dataset relevant to your own work. This project thread intensifies across the in‑person days, culminating in a short presentation. If you wish to develop your work further, you may submit a post‑course written analysis for an additional ECTS credit, equivalent to approximately 25 hours of additional work.
Images as data in social science research – research design, data sources, image‑processing fundamentals, computer vision principles, and the ethical responsibilities that accompany automated visual analysis. You will be introduced to pre‑recorded course videos and begin identifying potential research questions and datasets for your project.
Supervised approaches using pre‑trained models, unsupervised clustering and embedding methods, and the evaluation and validation of automated outputs for research purposes.
Gap period: Between the online and in‑person sessions, you will complete a structured assignment applying classification methods to a provided dataset, write a short critical reflection on the outputs, document your project dataset and research question, and complete assigned readings on multimodal methods.
Object and face detection as applied examples, followed by the conceptual foundations of multimodal analysis – how images and text interact in digital communication and how computational methods can capture this. You will develop and discuss your project designs.
Hands‑on work with CLIP‑style models for zero‑shot classification and cross‑modal embeddings, a conceptual overview of larger VLMs, and dedicated project work time with individual consultation.
You will present your project outlines or preliminary analyses, individually or in small groups depending on cohort size, followed by collective reflection on methodological choices and next steps.
Throughout the course, you will work with real datasets drawn from a range of social science contexts and are encouraged to apply methods directly to your own research questions.
The course is structured into five live sessions, each lasting 3 hours. The first two sessions will take place on Thursday 3 – Friday 4 September, online. The remaining three sessions will take place from Tuesday 8 – Thursday 10 September at Jagiellonian University. You must attend all sessions to complete the course.
The instructor will also conduct Q&A sessions and offer designated office hours for one-to-one consultations.
You are expected to have basic programming experience in Python or R – sufficient to load data, run scripts, and interpret outputs. No prior knowledge of computer vision, image analysis, or machine learning is required. Some familiarity with social science research design is helpful but not mandatory.
The course is designed at an intermediate level.
You must bring a laptop with Python and/or R installed.
A setup guide will be provided in advance; completing this before the first session is essential.
You should expect approximately 75 hours of total engagement, distributed across four phases:
If you opt for the post-course assignment – a written analysis developing the project presented on Day 5 – you should budget an additional 25 hours of work. This assignment is optional and carries an additional ECTS credit.
If you have registered and paid for the course, you will be given access to our Learning Management System (LMS) approximately two weeks before the course start date. Here, you can view course materials such as pre-course readings.
This course description may be subject to subsequent adaptations (e.g. taking into account new developments in the field, participant demands, group size, etc.). Registered participants will be informed at the time of change.
By registering for this course, you confirm that you possess the knowledge required to follow it. The instructor will not teach these prerequisite items. If in doubt, please contact us before registering.