TextBlob Sentiment Analysis Python Example

Sentiment Analysis can assist us with unraveling the mind-set and feelings of general people and assembling keen data with respect to the unique situation. Sentiment Analysis is a cycle of examining information and characterizing it dependent on the need for the examination.

These sentiments can be utilized for superior comprehension of different occasions and the effect brought about by it. Sentiment examination is an algorithm that performs calculations to classify text as positive/negative. To perform sentiment analysis using Python, we would need TextBlob library.

The TextBlob is a natural language processing library and is basically used for processing textual data. It has several functionalities such as tokenization, stemming, language translation, sentiment analysis, text classification and much more.

Here is the command to install TextBlob library using pip tool -

pip install textblob

The successful installation of this library looks as in the below screenshot.

Sentiment Analysis Simple Example

These are some examples to determine Sentiment Analysis in Python using TextBlob.

from textblob import TextBlob

b1 = TextBlob("Hii Sham! How are you?")

print("b1 = " + format(b1.sentiment))

b2 = TextBlob("I am fine and you?")

print("b2 = " + format(b2.sentiment))

b3 = TextBlob("I will be happy to see you again")

print("b3 = " + format(b3.sentiment))

b4 = TextBlob("The Pin of South Delhi is 110067.")

print("b4 = " + format(b4.sentiment))

The above code returns the following output -

Here, TextBlob returns two categories of subject- Polarity and Subjectivity.

Polarity is a float value within the range [-1.0 to 1.0], -1.0 defines a negative sentiment and 1.0 defines a positive sentiment. Negation words reverse the polarity.

Subjectivity is a float value within the range [0 to 1.0]. Subjectivity evaluates the measure of trustworthy and verifiable data contained in the content. The higher subjectivity implies that the content contains closely-held conviction instead of genuine data.

We calculated polarity and subjectivity for "I will be happy to see you again". For this particular example, polarity = 0.8 and subjectivity is 1.0, which is good. Similarly, we calculated polarity and subjectivity for "The Pin of South Delhi is 110067" and got polarity = 0.0 and subjectivity is 0.0. This sentence does not have any words that had a polarity in NLTK training set or TextBlob returns a weighted average sentiment score over all the words of the sentence.

Related Articles