Computer assisted text analysis in the social sciences

We use the term "Computer Assisted Text Analysis" in a broad sense to refer to a range of current techniques from quantitative social science and content analysis to 'data mining' and 'text classification', including the analysis of open-ended survey questions, transcribed interviews and speeches, wherever, in fact, the researcher is confronted with data in the form of natural language texts of social scientific interest. These methods are often used in exploratory data analysis, but can also be applied systematically with moderate statistical rigour in the development and testing of hypotheses at various theoretical levels, ranging from the statistics of word usage to changes within or between discourses over time. The general approach is in the tradition of content analysis, by which words which occur together in relatively close proximity in the same context are interpreted as relating to a common theme or concept in the discourse studied. We review a comprehensive set of tools to identify and visualize structures of co-occurrence of words and concepts both within, and in comparing, a number of texts. These produce results not essentially different from those reached by representing word co-occurrences in terms of network analysis or neural network programming using schematic linguistic templates of various kinds. A comparison of the relational data analysis vs. a dictionary-based MDS approach shows that these provide very close if not identical results, despite the fact that the underlying assumptions are frequently represented as different theoretical approaches.