Identifying epochs in text archives
Tobias Blanke, JON E. WILSON · 2017
This paper develops an automated approach to the `distant reading' of textual archives in order to classify epochs in the use of language and examine their particular characteristic. It classifies epochs by applying a series of standardised dictionaries to map the semantics of government documents, using the changing frequency of terms in these dictionaries to identify moments of rupture in language. It then tests a variety of techniques to chart the relationship between the changing shape of individual linguistic elements and aggregate patterns, particularly topic models and word2vec word embeddings. The result are a set of largely automated tools for understanding the structure of digital textual archives.