Hands-On NLTK Tutorial
The hands-on NLTK tutorial in the form of Jupyter notebooks
NLTK is one of the most popular Python packages for Natural Language Processing (NLP).
Index of Jupyter Notebooks
|1.1 Downloading Libs and Testing That They Are Working
Getting ready to start!
|1.2 Text Analysis Using nltk.text
Extracting interesting data from a given text
|2.1 Deriving N-Grams from Text
Creating n-grams (for language classification)
|2.2 Detecting Text Language by Counting Stop Words.ipynb
A simple way to find out what language a text is written in
|2.3 Language Identifier Using Word Bigrams
State-of-the-art language classifier
|3.1 Bigrams, Stemming and Lemmatizing
NLTK makes bigrams, stemming and lemmatization super-easy
|3.2 Finding Unusual Words in Given Language
Which words do not belong with the rest of the text?
|3.3 Creating a POS Tagger
Creating a Parts Of Speech tagger
|3.4 Parts of Speech and Meaning
Exploring awesome features offered by WordNet
|4.1 Name Gender Identifier
Building a classifier that guesses the gender of a name
|4.2 Classifying News Documents into Categories
Building a classifier that guesses the category of a news item
|5.1 Sentiment Analysis
Is a movie review positive or negative?
|5.2 Sentiment Analysis with nltk.sentiment.SentimentAnalyzer and VADER tools
More sentiment analysis!
|6.1 Twitter Stream (and Cleaning Tweets)
Live-stream tweets from Twitter
|6.2 Twitter Search
Search through past tweets
|7.1 NLTK with the Greek Script
Using NLTK with foreign scripts
|8.1 The langdetect and langid Libraries
Useful libraries for language identification
|8.2 Word2Vec (gensim)
H. Z. Sababa — hb20007 — [email protected]
Distributed under the MIT license. See
LICENSE for more information.