Infrastructures for Cultural Analytics, Digital Humanities, Text Analysis, and NLP
I build tools and infrastructures for analyzing, collecting, and manipulating texts, so that we can better understand books and other textual cultures. Some of my recent projects have included Macro-Etym, a tool for analyzing the etymologies of a text; Text-Matcher, a text reuse detection tool, good at identifying when a text quotes from another; Corpus-DB, an API for Project Gutenberg and other text repositories; and Chapterize, a tool for splitting a book into its chapters. I also lead the Open-Editions project, which aims to produce richly-annotated editions of classic works of literature, and the Git-Lit project, which publishes the British Library's digital books through GitHub.
I'm a PhD candidate in English and Comparative Literature at Columbia University, where I work in the Literary Modeling and Visualization Lab of the Group for Experimental Methods in the Humanities. Our group has no funding of its own, and my graduate student funding is very modest, so donations (of money, cryptocurrency, and/or code) are deeply appreciated.
JonathanReeve té els següents comptes en altres plataformes:
text-matcher 35 Actualitzat fa 2 mesos
A simple text reuse detection CLI tool.
corpus-db 35 Actualitzat fa 5 mesos
A textual corpus database for the digital humanities.
late-style-PCA 8 Actualitzat fa 1 any
An attempt to experimentally test Edward Said's claims about late style using computational text analysis and principal component analysis.
chapterize 32 Actualitzat fa 1 any
A simple tool for splitting up an ebook into its chapters. Works well with Project Gutenberg texts. May also be used to clean up books for computational text analysis.
chapter-experiments 0 Actualitzat fa 2 anys
Quantitative analyses of novelistic chapters. Diachronic analyses of chapter lengths, numbers of chapters, linguistic patterns within chapters.
sentence-trees 1 Actualitzat fa 3 anys
Experiments with sentences as trees.
character-attribution 2 Actualitzat fa 3 anys
Probabilistic attribution of character voices in fiction.
allusion-detection 4 Actualitzat fa 3 anys
Computational intertextuality detection in Python. Fuzzy string matching, approximate string matching.
JonathanReeve es va unir fa 10 mesos.