Nltk Tutorial – Complete Guide

Welcome to this exciting journey into Natural Language Processing (NLP) with Python’s nltk module, where we’ll unravel the wonders of text analysis and manipulation. By the end of this tutorial, you’re going to step out with a newfound appreciation for language, machines, and the magic that happens when the two combine.

What is nltk?

NLTK, or Natural Language Toolkit, is a Python library specially designed for working with human language data. It introduces us to a variety of functionalities for text analysis such as classification, tokenization, stemming, tagging, parsing, semantic reasoning, and more.

In a world where 80% of data is unstructured, nltk allows us to bring structure to this chaos. From sentiment analysis of customer reviews to developing responsive chatbots, the applications of nltk are endless. Moreover, understanding nltk is a cornerstone skill in the rapidly growing field of Natural Language Processing.

NLTK is primarily for processing and analyzing text, spanning from basic tasks like counting word frequencies to advanced operations such as machine translation. It brings to us a proficient interface to work with human language and is widely applicable in fields such as linguistics, cognitive science, machine learning, and data science.

Are you ready for a captivating exploration of natural language and its interaction with machines? Then fasten your seat belts because we are about to venture into the enchanting world of nltk and Python. Stay with us to unravel more about this topic.

CTA Small Image

Installing NLTK

Before we can dive into text analysis with NLTK, we need to make sure it’s installed. Installing NLTK in Python environment is as simple as running the pip command. Just enter the following in your command prompt:

pip install nltk

After installation, you can confirm it by trying to import the nltk module in a Python script or interpreter:

import nltk


Tokenization is a fundamental step in natural language processing which involves splitting text into words, phrases, symbols, or other meaningful elements, known as tokens.

In NLTK, we can perform tokenization using the word_tokenize function:

import nltk'punkt')

from nltk.tokenize import word_tokenize

text = "Welcome to Zenva's Python and nltk tutorial!"
tokens = word_tokenize(text)


The output will be: [‘Welcome’, ‘to’, ‘Zenva’, “‘s”, ‘Python’, ‘and’, ‘nltk’, ‘tutorial’, ‘!’]


Part of Speech (POS) tagging is a process of labelling words in a text as corresponding to a particular part of speech, like noun, verb, adjective, etc.

The NLTK pos_tag function can be used to do this:

import nltk
from nltk import pos_tag'averaged_perceptron_tagger')

sentence = "We are learning NLP with nltk"
tokens = word_tokenize(sentence)
tags = nltk.pos_tag(tokens)


The output will be: [(‘We’, ‘PRP’), (‘are’, ‘VBP’), (‘learning’, ‘VBG’), (‘NLP’, ‘NNP’), (‘with’, ‘IN’), (‘nltk’, ‘NN’)]


Lemmatization in NLP is the process of reducing a word to its base or root form. It’s more sophisticated than stemming as it takes into account the morphological analysis of the words.

Lemmatization can be done in NLTK using the WordNetLemmatizer:

import nltk
from nltk.stem import WordNetLemmatizer'wordnet')

lemmatizer = WordNetLemmatizer()

The output will be: ‘run’ – which is the base form of ‘running’.

Stop Words

In NLP, stop words are words that are filtered out before processing because they are primarily the most common words such as ‘is’, ‘in’, ‘at’, ‘the’, ‘and’, etc. NLTK has a built-in list of stop words in 16 different languages.

Below is a code to remove stop words from a text:

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize'stopwords')

stop_words = set(stopwords.words('english'))

sentence = "We here at Zenva are interested in Natural Language Processing"

words = word_tokenize(sentence)

filtered_sentence = [word for word in words if not word in stop_words]



Stemming is the process of reducing inflection in words to their root forms such as mapping a group of words to the same stem even if the stem itself is not a valid word in the language.

Let’s use NLTK’s PorterStemmer tool to perform stemming:

from nltk.stem import PorterStemmer
from nltk.tokenize import word_tokenize

ps = PorterStemmer()

# choose some words to be stemmed
words = ["program", "programs", "programmer", "programming", "programmed"]

for w in words:
    print(w, " : ", ps.stem(w))

Synonyms and Antonyms from NLTK’s WordNet

NLTK comes with a semantic reasoner, WordNet, which among other things, allows us to find synonyms and antonyms of words.

Below is a piece of code for finding synonyms and antonyms with NLTK’s WordNet:

import nltk
from nltk.corpus import wordnet

synonyms = []
antonyms = []

for syn in wordnet.synsets("happy"):
    for l in syn.lemmas():
        if l.antonyms():


Sentiment Analysis

Sentiment Analysis, also known as opinion mining, is a powerful tool you can use to build smarter products. It’s a natural language processing problem where text is understood and the underlying intent is predicted.

Here’s a simple code of how sentiment analysis can be achieved:

from nltk.sentiment.vader import SentimentIntensityAnalyzer
import nltk'vader_lexicon')

sentences = ["I love this phone", "This is an awful library"]

sid = SentimentIntensityAnalyzer()

for sentence in sentences:
    ss = sid.polarity_scores(sentence)
    for k in sorted(ss):
        print('{0}: {1}, '.format(k, ss[k]), end='')

That’s it! With these valuable tools in your arsenal, you’re ready to dive into the world of Natural Language Processing with Python’s NLTK module. With continuous practice, the operations will become second nature to you, and you’ll be manipulating and analyzing text like a pro.

Where to go next?

You’ve taken the first steps into the captivating world of Natural Language Processing with Python’s nltk module. You’ve witnessed the power of machines to understand, analyze, and manipulate human language. But this is just the beginning. There’s so much more to learn and explore in the field of programming and NLP.

The Python Mini-Degree that we at Zenva offer is a great next step on this journey. It is a comprehensive collection of courses designed to take you from a beginner to a proficient Python programmer.

Not only does the curriculum cover coding basics, algorithms, and object-oriented programming, but it also ventures into game development and application development. Great projects like creating arcade games, a medical diagnosis bot, and a to-do list app are included in the coursework. Completing these courses will help you develop a rich portfolio of Python projects and prepare you for a dynamic career in various industries. Furthermore, we regularly update our courses to keep pace with the latest developments in technology.

Whether you’re starting your coding journey or delving deeper into the world of Python, we have the perfect resources to help you progress. For a more extensive range, you can check out our entire list of Python Courses. It’s a long journey ahead and we at Zenva are excited to guide you each step of the way. Embrace the learning journey and discover where Python and nltk can take you!


Language is central to our human experience, and the ability to analyze and interpret this language is a powerful tool indeed. Therefore, learning natural language processing with Python’s nltk module can be a game-changing skill for your professional toolkit. Whether you’re a software developer, a data scientist or an AI enthusiast seeking to make sense of the vast sea of unstructured text data, nltk is a great way to start your journey.

At Zenva, we are committed to providing high-quality, relevant and engaging content to help you acquire such in-demand skills. Explore our Python Programming Mini-Degree and broaden your knowledge while working on practical projects. The world of coding and language processing is vast and exciting. Be daring, be curious, and dive in with us at Zenva!

Did you come across any errors in this tutorial? Please let us know by completing this form and we’ll look into it!

Python Blog Image

FINAL DAYS: Unlock coding courses in Unity, Godot, Unreal, Python and more.