From Brede Wiki

Jump to: navigation, search
Software (help)
Description: Natural language processing
Developer: missing developer
Language: Python
License: Apache 2.0
Parent(s): Python
Database(s): Wikipedia
Feature(s): Part-of-speech tagging, Tokenization, Machine learning

NLTK (Natural Language Toolkit) is a Python package for text mining.

Movie review sentiment analysis example: [1]

Among the developers are Edward Loper and Steven Bird.


[edit] Books

  1. Natural language processing with Python (book by the developers)
  2. Python text processing with NLTK 2.0 cookbook

[edit] Papers

  1. Getting started on natural language processing with Python
  2. NLTK: the Natural Language Toolkit (2002)
  3. NLTK: the Natural Language Toolkit (2004)
  4. NLTK-Lite: efficient scripting for natural language processing

[edit] Applications

  1. Annotating named entities in twitter data with crowdsourcing (named entity recognition)
  2. Good friends, bad news - affect and virality in Twitter (use the naïve Bayes classifier)
  3. Reading tea leaves: how humans interpret topic models (use of stopwords(?))

[edit] Related software

  1. Pattern (software)
  2. Redshift
  3. spaCy
Personal tools