In our paper, we present an overview of Natural Language Processing (NLP) methods, which developed parallel with the spread of ‘Big Data’ paradigm. We present the most promising methods for social sciences, the specific research questions they can answer and the methodological features that distinguish them from classic quantitative methods. These methods go far beyond classic quantitative text analysis based on simple word frequencies. Their modelling logic arises from machine learning methods; hence, it is substantially differing from the classic social science logic that seeks for explanation and casual effects. Our goal is to inspire Hungarian social scientists by providing an insight into a less-institutionalized area, since we believe that at an international level, text mining will be a standard method for empirical social science research within a few years.