MapOfScience.gml (1.13 MB)
A Wikipedia Based Map of Science
Version 5 2020-01-20, 18:10
Version 4 2020-01-20, 18:09
Version 3 2020-01-20, 18:00
Version 2 2020-01-18, 11:45
Version 1 2020-01-18, 07:48
dataset
posted on 2020-01-20, 18:10 authored by Alberto CalderoneAlberto Calderone15th January 2020 - A Map of Science. v. 1.0
Description:
A network which shows the similarities among different branches of science. It's based on Wikipedia pages in outline of natural, formal, social and applied sciences plus Data Science, which is not yet included (18 Jan. 2020). All pages called "Outline of X" were ignored. Pages are pre processed to get the main content with regular expressions. Stop words removal, lemmatization with WordNetLemmatizer in NLTK. Edges represent cosine similarity and filtered calculating zscore leaving only edges with a zscore > 1.959964 . Isolated nodes were removed.
Materials:
R, python, igraph, nltk, d3, javascript, html, wikipedia
Contact:
Alberto Calderone - sinnefa@gmail.com
Preview:
http://www.sinnefa.com/wikipediasciencemap/
