In recent work (an early working paper version can be found here), I employed so-called text mining methods such as structural topic modelling to examine all 2,135 speeches by ECB Executive Board members between February 1997 and October 2019. These new methods from the rapidly growing field of digital humanities allowed me to identify and analyse a significant semantic change that occurred in ECB communication in the transition from Great Moderation to Great Recession. The methodology also allowed for a structured and empirical assessment of the hypothesis that central bankers used ‘lessons from the past’ during the crisis. The quantitative and qualitative results indicate that references to historical analogies indeed increased at the height of the crisis (2009–11) but often served only rhetorical functions. In my talk, I will present some of the text mining methods that I have applied as part of this research and then use the empirical results as a starting point for a broader methodological discussion, reflecting on how digital humanities approaches are changing our research designs, and how the results obtained using these new methods differ from those obtained via traditional close reading.
As usual in this discussion series, a short summary of the main theses will be circulated among the registered participants a few days before the talk. It is not necessary to read the full working paper.