Name: Jonathan Armoza
Type: User
Company: New York University
Bio: PhD@NYU English. Digital humanist, Xoogler, Game developer. I develop models/data viz of large text corpora using machine learning, Python, JS.
Location: Montréal, QC
Jonathan Armoza's Projects
Repository of code for Art of Literary Modeling
Horror beyond imagination. A dissertation repository.
Repository of various generic libraries developed for my digital humanities research
Using probabilistic matrix factorization to operationalize Harrison Hayford's draft hypotheses of Moby-Dick
An inarguably well-designed Jekyll theme.
My personal website
"Topic Words in Context – Dickinson, The Fascicle, and the Topic Model" - Master's Thesis from McGill University (2016)
Narrative chart of the topics of 13K+ PubMed neuroscience articles (1998-2018)
NeuroData Science Lab Website
Non-negative Matrix Factorization and the Fascicles of Emily Dickinson
Submission guideline for neurolibre
Papers, slides, and other materials from my talks
Slides from my talk at DH2017: How to Close Read a Topic Model
This repository is intended to give tutorials for the lab, that can be used to learn some usefull tools.
Model selection criterion and Mark Twain's Autobiography
Topic Words in Context (TWiC) is a highly-interactive, browser-based visualization for MALLET topic models
The newest version of the topic modeling visualization, "Topic Words in Context"
TWiC Close Reading is a program that produces interactive HTML files of texts topic-modeled by MALLET
Book/Page level prototype for "Working from Scraps", a project looking at the scrapbooks of Scottish poet Edwin Morgan
VueJS source code and data for 'Working from Scraps' - a collaboration with Bridget Moynihan looking at the scrapbooks of Scottish poet Edwin Morgan