The textbook titled Text Mining and Artificial Intelligence in R, produced in the poltextLAB text mining research group of the HUN-REN Centre for Social Sciences, presents the most important practical aspects of the application of quantitative text analysis methods in social sciences. The online version of the book is regularly updated by the authors Miklós Sebők, Orsolya Ring and Ákos Máté.
The interpretation and quantitative analysis of texts as data, i.e. text mining, is one of the fastest developing areas of international social science research and one of the most obvious entry points for researchers in this field to use of artificial intelligence and machine learning.
Quantitative text analysis techniques used in modern social science - name recognition, opinion analysis, topical modelling, supervised text classification - are presented using R, one of the most commonly used programming languages, making the textbook suitable for newcomers, even if they barley have any understanding of coding. Based on examples on mostly new, Hungarian corpora, readers can learn the methods of quantitative text analysis in Hungarian step-by-step.
The research on which the book is based was carried out by the Centre for Social Sciences, within the MILAB project.