Introduction to Text Analysis with R

This tutorial will introduce some principles of text analysis using R. A first introductory part will show some examples of text analysis in practice in social research. A second part will deal with some basic text analysis in graphical mode (just mouse clicks, no coding) using R Commander. Although easy, this method has several limitations, so we go to the third and more extensive part, that will deal with text analysis writing code. There are a lot of packages in R for text analysis, some of them using tidy principles (don't worry for now), and some differences to other approaches. We will see differences between bag of words and semantic parsing. Data cleaning (or data wrangling) is also a (great) part in preparing data for analysis, and we will see the typical steps, like removing stopwords, stemming and lemmatization, etc. Data visualization like simple word frequencies, different ways to do different wordclouds, frequency of words and dictionary methods such as concept frequency, some basic sentiment analysis (specially for non-English speakers). Finally, we will enter into some basic machine learning, like topic modeling.