Courses

Web infrastructure, content management systems, strategic communication planning, AI implications, and digital analytics. Students learn to critically evaluate and implement web communication strategies.

Statistical foundations for communication students. Descriptive statistics, probability theory, hypothesis testing, and inferential statistics in R (tidyverse, ggplot2), with examples from media and communications.

Data types and sources, R programming, data visualisation, web scraping, machine learning, text analysis, and reproducible reporting. For graduate sociology and social science students.

Computational approaches to social media data. Platform-specific analysis (Twitter, Facebook, Instagram, LinkedIn), data infrastructure, statistical methods, and open-source analytics tools.

Computational text analysis from data preparation through NLP. Dictionary methods, supervised and unsupervised machine learning, topic modelling, and text clustering in R.

R programming, descriptive statistics, data visualisation, hypothesis testing, categorical analysis, ANOVA, and linear regression for undergraduate social science students.

From frontier ideas to a working agentic pipeline: a working paper rendered live from Eurostat data, and a fully reproducible open-source repository you can clone and run.

Agentic AI for methodological research: moving from chat-prompting to delegating a whole task the model plans, executes, and verifies before returning for approval. The repository is itself a worked example of the framework.

Day 1 — transformers and RAG, academic integrity and APA 7, Perplexity for sourcing, Gemini Deep Research, structuring a research proposal with Claude. Day 2 — agentic coding with Claude Code, IDE integration, LLM notebooks for exploratory analysis, and AI-assisted academic writing in Croatian. Funded under the National Recovery and Resilience Plan (NextGenerationEU).