id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
plumb-humanities-2021		plumb-humanities-2021	2021-02-23	14	.pdf	application/pdf	7195	599	45	Respondents such as Mark Algee-Hewitt pointed out that literary scholars employ computational statistical models in order to reveal something about texts that human readers Machine learning, and word embedding algorithms in particular, may have a unique ability to shift this conversation into new territory, where scholars Acknowledging this helps contextualize machine learning algorithms for text analysis tasks in the humanities, but also highlights data curation challenges This naturally raises questions about how machine learning algorithms like word embeddings are implemented for text analysis, and how they Based on the potential for word embeddings to model semantic spaces for different corpora and compare the distribution of terms, the next step was to build a corpus of non-canonical Designing humanities research with novel word embedding models stands to widen the territory where machine learning engineers look for conceptual concepts Systematic data curation, combined with word embedding algorithms, represent a new interpretive system for literary scholars.	./cache/plumb-humanities-2021.pdf	./txt/plumb-humanities-2021.txt