ABSTRACT
This chapter looks at the philosophical and methodological issues of unstructured text data. Text data mining allows for a much faster organization and analysis of text data than what could be done manually as it uses semiautomated data mining techniques. The chapter presents a rudimentary demonstration of Text Data Analytics using corpus and computational linguistics. It also considers how the concept of sustainable transportation is discussed in the US Congress. Public policies, regulations, and government directives are important components of greater sustainability. The words as data techniques are only used with computer-assisted analysis. In contrast, much of the work in Critical Text Analysis requires a careful, close reading of texts. The chapter follows the methodology outlined in Schuelke-Leech et al. and Schuelke-Leech and Barry. This methodology accounts for the complexity and volume of large unstructured datasets, rather than simplifying the dataset by removing noise words and order.
