Toward a 'Text as Data' Approach in the History and Methodology of Economics : An Application to Adam Smith’s Classics

The fields of the history and methodology of economics have recently experienced a quantitative turn. Among the quantitative tools and methods recently used, text mining has received less attention. In this article, we apply a “text as data” approach to the study of Adam Smith's The Wealth of Nations and The Theory of Moral Sentiments. We first study these two classics through the lenses of readability and lexical richness indicators and sentiment analysis. We then determine the most relevant words and topics in the two books and, as case studies, we examine the specific topics of opulence, poverty, prosperity, sympathy, tax, war, wealth, and woman. Our results confirm some of the well-known differences between the two books (thus supporting the argument that text mining is a powerful and generally reliable tool for exploratory research on unknown documents), but also provide new insights about them