As part of a larger exploration of the British Culture of Litigation (from a literary perspective), we are working on developing text-mining techniques with the corpus of Proquest British Periodicals, which contains (of its total 3.4 mil) roughly a million articles in the relevant timeframe of 1770-1850 produced in several hundred periodicals. Our goal is to use this database to produce and analyze the wider discourse about the law, justice, courtroom procedure, evidence, proof, etc., and the general intrusion by law into the everyday discourse of the periodicals, the most read format of the era. Toward that end, we are hoping to use HuggingFace, in conjunction with other approaches, for certain technical matters, such as improving the OCR of the database, and for analytic approaches, such as topic modeling, wordtovec, to get a stronger sense of the resonances of law generally and within specific discourses, such as theatricality, science, and religion. We hope similar methods will allow a stronger understanding of the public response to various innovations and spectacles within the space of litigation, such as cross-examination, one-farthing verdicts, and crim-con trials (these were civil trials for adultery, treated as if criminal—and marketed as lurid). In its broadest methodological scope, we seek to demonstrate that text-mining legitimately supplements and improves other techniques of literary analysis for understanding crucial cultural constructs and transformations.
If you have any questions about this project and/or are interested in joining the team, please reach out to mark.schoenfield@vanderbilt.edu and clifford.anderson@vanderbilt.edu.