Sentiment analysis Python

Sentiment analysis Python Tutorial: These is an easy way to use cloud service that will provide API. The sentiment analysis is the NLP task of data scientists that need to perform a task. The data generated is required to process the insights. Here the NLTK is used for making sense and falls under the filled of natural language processing. Here the sentiment analysis is a common task that involves text and texts which are predefined. The NLTK package is used with tweets and a model to classify the sample as negative and positive. It refers to the techniques which extract options from a piece of text that is written in natural language. Also find out whether the piece of text is positive, negative or neutral. The sentiment analysis is included in the artificial intelligence and machine learning and finds the use of industries.

Working:-

We use this method,

By using open-source libraries
By using an API
Then both of them have advantages.

Using Open-Source Libraries:-

It is an open-source library that has an independent technique used for implementation.
They will require a lot of resources and install hardware.
It is complicated because the code is long.

Using an API:-

The Saas API is used for those who have fewer resources while ML.
The creation of sentiment analysis is simple by using Saas API.
Here the API make task simple and create an analysis model.

While using sentiment analysis much code is required.

Here steps to be followed for sentiment analysis as,

Create an account
Install the Python SDK (Make sure it JSON integration is enabled)
Write a specific set of code (code differs among APIs)
Copy/paste the text you need to analyze
See the results

Sentences as,

That tree is ugly
That flower smells nice

The ugly and nice are the keywords in sentence as negative because it has ugly and positive because of nice.

Applications:-

There are many applications in industries as,

Political Campaigns:-

They must be aware of the sentiment on the different topics related to constituencies.
The political parties and campaign managers will use sentiment analysis to find out the opinion of the general public.
Twitter is also used as sentiment analysis for this purpose as they take data from people’s tweets on a specific topic.

Customer Experience:-

Here some companies use sentiment analysis to check customer’ reviews.
They will not give a review directly and post their opinions on social media.
By using sentiment analysis companies check the reviews of a particular product.
After finding out the opinion of the customer’s organization will improve the need for a product.

Step 1 Competitive Analysis:-

We find an opinion on your competitor’s products by using sentiment analysis.
It also helps the companies in understanding competition is right and mistakes.

Pip install nltk==3.3

Then we will import the nltk module in the python interpreter.
import nltk

Then we download the sample tweets from the NLTK package:
nltk.download ('twitter_samples')

Then we run a command from the Python interpreter to download and store the tweets.
After downloading the samples it is available for your use.

Step 2 Tokenizing the Data:-

Here the data is a process called tokenization in small parts called tokens.
The sequence of characters in text that serve the unit used to create a token.
They are used to create tokens by words, hash tags, and characters.
We create a new .py file to hold your script.
nano nlp_test.py
from nltk.corpus import twitter_samples
We import three datasets from NLTK that contain various tweets to train and test the model,
from nltk.corpus import twitter_samples
positive_tweets = twitter_samples.strings ('positive_tweets.json')
negative_tweets = twitter_samples.strings ('negative_tweets.json')
text = twitter_samples.strings ('tweets.20150430-223406.json')
tweet_tokens = twitter_samples.tokenized ('positive_tweets.json')[0]

Step 3 Normalizing the Data:-

It helps the word with same meaning and different form without normalization.
The stemming process will remove affixes from word and simple verb.
From nltk.tag import pos_tag
From nltk.stem.wordnet import wordNetLemmatizer
Def lemmatize_sentemce (tokens):
Lemmatizer=WordNetLemmatizer ()
Lemmatized_senetence= []
For word, tag in pos_tag (tokens):
If tag.startswith (‘NN’):
Pos=’n’
Elif tag.startswith (‘VB’):
Pos=’v’
Else:
Pos=’a’
Lemmatized_senetence.append (Lemmatizer_lemmatize (word, pos))
Return lemmatized_Senetnce
Print (lemmatize_Senetence (tweet_tokens [0]))

Benefits:-

Sentiment analysis will help business process in much amount.
They help for immediate identification of the situations like real time analysis.
Applications:-