JasonKessler/Scattertext-PyData
Notebooks for the Seattle PyData 2017 talk on Scattertext
This project helps data scientists, researchers, and content strategists analyze and visualize how language differs between categories of documents. You input collections of text documents (e.g., political speeches, product reviews, scientific papers) grouped by categories like political party, gender, or topic. It outputs interactive scatter plots that highlight the words and phrases most characteristic of each category, making it easy to spot linguistic distinctions.
141 stars. No commits in the last 6 months.
Use this if you need to quickly identify and visualize the unique language patterns present in different groups of text documents.
Not ideal if you're looking for advanced sentiment analysis or complex topic modeling beyond comparing word usage frequencies.
Stars
141
Forks
52
Language
HTML
License
—
Category
Last pushed
Jan 12, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/JasonKessler/Scattertext-PyData"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
dessertlab/cti-to-mitre-with-nlp
Replication package for the paper "Automatic Mapping of Unstructured Cyber Threat Intelligence:...
maastrichtlawtech/law3027-advanced-legal-analytics
π Materials for Advanced Legal Analytics (LAW3027) @ Maastricht University.
HanyangTechAI/2022_Project_Team1
2022 HAI 1ν νλ‘μ νΈ λ°©μΈ λ²μκΈ° κ°λ°μ μν λ ν¬μ§ν 리μ λλ€.
ds-modules/LEGAL-190-FA22
UC Berkeley LEGALST 190 Fall 2022
gyunggyung/Multipurpose_Word_Cloud
μκΈ°μκ°μ, κ°μ¬, μΉ΄μΉ΄μ€ν‘ λν λ± μ΄λ ν κ²μ λν κΈμ μμ μ΄ μνλ κ·Έλ¦Όκ³Ό λ°©μμΌλ‘ ννν΄μ€λλ€.