I have created a catalog of .3 million open access items, mostly journal articles and etexts. See: https://t.co/UK1q5cZwvZ The ultimate goal is enable to people: search, refine, and create a study carrel from the results.
The other day I wrote an essay rooted in a bibliography on DEI in libraries and compiled by
@peggygriesinger. I used the Reader to help me with the analysis. See: https://t.co/nJq9pSBy5T
Yesterday I (#distantreader) finished writing a blog posting on the topic of visualizing the size and scope of a library collection. Fun with RDF. https://t.co/vlEINfRfe6
Modern Alchemy - This presentation describes and demonstrates the Distant Reader. Given an almost arbitrary amount of unstructured data (text), the Reader creates a corpus, does analysis against it, and outputs a data set -- information -> https://t.co/llpr4ivC1c
Introducing the Distant Reader Toolbox, a command-line tool for feature extraction, semantic indexing, topic modeling, and all around analysis against a corpus --> https://t.co/JRShlXD08I
I have been writing code and documentation intended to assist students, researchers, and scholars in the use of #distantreader study carrels. The work is coming along well: https://t.co/vbHMMBekYz
In the coming week I will be facilitating a hands-on workshop on the #distantreader, and I have posted the instructions at https://t.co/2EpoXe0ggi Feedback welcome.
Using the #distantreader, I tried to learn about "mRNA". First I created a data set of 90 articles: https://t.co/VPpVkAELR2 The keyword cloud looked like this:
Using information extraction techniques, I created lists. The first was a list "mrna is" sentences. "mRNA is a promising approach." https://t.co/5AunDNbZoW