Our Textbook

About our textbook

Our textbook introduces you to the specific problems of textmining and the application of artificial intelligence in the social sciences.

Text-as-data and quantitative analysis, or textmining, is one of the fastest growing trends in international social science research. Textmining is also one of the most obvious entry points for social scientists into the field of research using artificial intelligence, including machine learning.

For the first time in the Hungarian textbook market, we present a step-by-step introduction to quantitative text analysis techniques used in international social science, such as word recognition, opinion analysis, topical modelling and supervised learning-based text classification. The analyses to demonstrate our methods were carried out using R, one of the most commonly used programming languages. The material in this book can be learned with even a minimum knowledge of programming and is therefore recommended for complete beginners. With the interest of Hungarian readers in mind, the vast majority of our examples are based on new Hungarian-language corpora, which provide a basis for learning about quantitative text analysis methods in Hungarian.

The Hungarian language textbook  and scripts, data are available  here.