seanfobbe , to histodons group
@seanfobbe@fediscience.org avatar

🔔 NEW Dataset 🔔

The Corpus of Resolutions: UN Security Council (CR-UNSC)

✅ 2722 resolutions (1946-2024)
✅ All six UN languages
✅ 82 Variables
✅ Enhanced OCR
✅ Citation Data
✅ and
✅ Formats: CSV, PDF, TXT, GraphML, BibTeX

Full dataset: https://zenodo.org/doi/10.5281/zenodo.7319780

Source Code: https://zenodo.org/doi/10.5281/zenodo.7319783

Blog: https://seanfobbe.com/posts/2024-05-06_new-dataset-corpus-of-resolutions-un-security-council/

@histodons @law @politicalscience @rstats

dustinstoltz , to sociology group
@dustinstoltz@fediscience.org avatar

My book Mapping Texts (co-authored with @mtaylor_soc ) ships at the end of this month if you order directly from Oxford University Press!

The book's website is now live: https://www.textmapping.com

More pages on the site will go live once the book is officially published!

Pre-order @ https://bit.ly/3NOu5kG


@rstats @sociology @academicchatter

dustinstoltz OP ,
@dustinstoltz@fediscience.org avatar

@mtaylor_soc @rstats @sociology @academicchatter

I also recently added several pretrained (static and diachronic) embedding models to the R package text2map.pretrained

https://culturalcartography.gitlab.io/text2map.pretrained/

Anyone who wants to play around with some well-known embedding models (like the HistWords COHA diachronic embeddings) can get up and running in R in a few minutes!

dustinstoltz OP ,
@dustinstoltz@fediscience.org avatar

@mtaylor_soc @rstats @sociology @academicchatter

More updates for !

We're now sharing all the code from our book Mapping Texts: https://gitlab.com/culturalcartography/mappingtexts/text2map.bookcode

Each folder corresponds to a chapter, and each script corresponds (roughly) to a section.

We run diagnostics on the scripts periodically to catch any issues and update them accordingly. Updates are documented here: https://www.textmapping.com/fixes/

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • kbinchat
  • All magazines
    •