Mastering Python for Data Science

Parts of speech tagging

Parts of speech tagging is one of the important tasks of text analysis. It helps tag each word based on the context of a sentence or the role that a word plays in a sentence.

Let's see how to perform part of speech tagging using nltk:

>>> pos_word_data = nltk.pos_tag(word_data)

>>> pos_word_data[ : 10]

[('Pundits', 'NNS'),
 ('and', 'CC'),
 ('critics', 'NNS'),
 ('like', 'IN'),
 ('to', 'TO'),
 ('blame', 'VB'),
 ('the', 'DT'),
 ('twin', 'NN'),
 ('successes', 'NNS'),
 ('of', 'IN')]

You can see tags, such as NNS, CC, IN , TO, DT, and NN. Let's see what they mean using this code:

>>> nltk.help.upenn_tagset('NNS')

NNS: noun, common, plural undergraduates scotches bric-a-brac products bodyguards facets coasts divestitures storehouses ...