Part of Speech Tagging using TextBlob

TextBlob module is utilized for creating programs to analyse text. One of the most powerful features that are included in the TextBlob module can be its Part of Speech tagging.

First, we will install TextBlob and run these commands:

It will then run TextBlob in addition to downloading the needed NLTK corpora. The installation process above can take a long time because of the huge number of chunkers, tokenizers, other algorithms, as well as all of the corpora that need to be downloaded.

In corpus linguistics, part-of-speech tag (POS tagging, also known as PoS tagging or POST) is also known as Grammatical Tagging or Disambiguation of the word category.

Here’s a list of the tags, with their meaning, and some examples:

CC : it is a coordinating conjunction

CD : it is a cardinal digit

DT : it is the determiner

EX : it is existential there (For example: “there is” … think of it like “there exists”)

FW : it is a foreign word

IN : it is a preposition/subordinating conjunction

JJ : this is an adjective for example: ‘big’

JJR : this is an adjective, for example: comparative ‘bigger’

JJS : this is an adjective, for example: superlative ‘biggest’

LS : it is a list marker for example: 1)

2)

MD : it is a modal for example: could, will

NN : it is a noun, for example: singular ‘desk’

NNS : it is a noun, for example: plural ‘desks’

NNP : it is a proper noun, for example: singular ‘Harrison’

NNPS : it is a proper noun, for example: plural ‘Americans’

PDT : it is a predeterminer for example: ‘all the kids’

POS : it is a possessive ending parent’s

PRP : it is a personal pronoun, for example: I, he, she

PRP$ : it is a possessive pronoun, for example: my, his, hers

RB : it is a adverb for example: very, silently,

RBR : it is a adverb, for example: comparative better

RBS : it is a adverb, for example: superlative best

RP : it is a particle give up

TO : to go, for example: ‘to’ the store.

UH : it is a interjection for example: errrrrrrrm

VB : it is a verb, for example: base form take

VBD : it is a verb, for example: past tense took

VBG : it is a verb, for example: gerund/present participle taking

VBN : it is a verb, for example: past participle taken

VBP : it is a verb, for example: sing. present, non-3d take

VBZ : it is a verb, for example: 3rd person sing. present takes

WDT : it is a wh-determiner for example: which

WP : it is a wh-pronoun, for example: who, what

WP$ : it is a possessive wh-pronoun for example: whose

WRB : it is a wh-adverb for example: where, when

Code:

Output:

[('Jack', 'NNP'), ('Jill', 'NNP'), ('and', 'CC'), ('Bill', 'NNP'), ('are', 'VBP'), ('living', 'VBG'), ('in', 'IN'), ('America', 'NNP'), ('Jack', 'NNP'), ('use', 'NN'), ('to', 'TO'), ('go', 'VB'), ('for', 'IN'), ('running', 'VBG'), ('every', 'DT'), ('morning', 'NN'), ('but', 'CC'), ('he', 'PRP'), ('got', 'VBD'), ('fever', 'RB'), ('last', 'JJ'), ('night', 'NN'), ('therefore', 'VBD'), ('her', 'PRP$'), ('will', 'MD'), ('not', 'RB'), ('be', 'VB'), ('going', 'VBG'), ('for', 'IN'), ('running', 'VBG'), ('tomorrow', 'NN'), ('this', 'DT'), ('would', 'MD'), ('be', 'VB'), ('his', 'PRP$'), ('first', 'JJ'), ('time', 'NN'), ('of', 'IN'), ('breaking', 'VBG'), ('his', 'PRP$'), ('running', 'VBG'), ('streak', 'NN'), ('jill', 'NN'), ('is', 'VBZ'), ('a', 'DT'), ('school', 'NN'), ('teacher.he', 'NN'), ('believes', 'VBZ'), ('in', 'IN'), ('meditation', 'NN'), ('he', 'PRP'), ('practice', 'NN'), ('mediating', 'VBG'), ('daily', 'RB'), ('for', 'IN'), ('an', 'DT'), ('hour', 'NN'), ('bill', 'NN'), ('is', 'VBZ'), ('a', 'DT'), ('fun', 'NN'), ('guy', 'NN'), ('for', 'IN'), ('him', 'PRP'), ('laughing', 'VBG'), ('is', 'VBZ'), ('the', 'DT'), ('best', 'JJS'), ('medicine', 'NN')]

In essence, the purpose of the POS tagger is to assign the linguistic (mostly grammar-related) details to the sub-sentential unit. They are also known as tokens, and, the majority of times, they correspond to symbols and words (e.g., punctuation).