• Home
  • Academic
  • Publications
  • Resources
  • Contact
  • Home
  • Academic
  • Publications
  • Resources
  • Contact

Code Notebooks

Analyzing the Properties of Episodic Word Lists

1/23/2017

 
The following code can be used to:
​1) Generate a list of words within a given frequency class (or a mix of frequency classes) from the ​SUBTLEXus database of word frequencies.
2) Automatically analyze the properties of a given list, including:
  • word frequency
  • word length
  • letter n-gram frequency
3) Compare a set of n lists on these same properties, as well as:
  • orthographic similarity (Levenshtein edit distance)
  • semantic similarity (word2vec)

Comments are closed.

    Code Snippets

    Introductory coding demos in Python. Click the file name in the lower left-hand corner to view full screen at Github.

    Archives

    February 2018
    January 2017
    December 2015
    March 2015
    June 2014
    April 2013
    December 2012

    Categories

    All
    Data Analysis
    Episodic Memory
    Language Processing
    N-gram
    NLP
    NLTK
    Social Media
    Stylometrics
    Web Scraping

Powered by Create your own unique website with customizable templates.