spacytextblob 3.0.1

A TextBlob sentiment analysis pipeline compponent for spaCy

spaCyTextBlob

A TextBlob sentiment analysis pipeline compponent for spaCy.

Version 3.0 is a major version update providing support for spaCy 3.0's new interface for adding pipeline components. As a result, it is not backwards compatible with previous versions of spaCyTextBlob. For compatability with spaCy 2.0 please use pip install spacytextblob==0.1.7.

Note that version 1.0, and 2.0 have been skipped. The numbering has been aligned with spaCy's version numbering in the hopes of making it easier to compar.

• Docs
• GitHub
• PyPi

Table of Contents

• Install
• Quick Start
• Quick Reference
• Reference and Attribution

Install

Install spaCyTextBlob from pypi.

pip install spacytextblob

TextBlob also requires some data to be downloaded before getting started.

python -m textblob.download_corpora

spaCy requires that you download a model to get started.

python -m spacy download en_core_web_sm

Quick Start

spaCyTextBlob allows you to access all of the attributes created by TextBlob sentiment method but within the spaCy framework. The code below will demonstrate how to use spaCyTextBlob on a simple string.

text = "I had a really horrible day. It was the worst day ever! But every now and then I have a really good day that makes me happy."

Using spaCyTextBlob:

import spacy
from spacytextblob.spacytextblob import SpacyTextBlob

nlp = spacy.load('en_core_web_sm')
nlp.add_pipe("spacytextblob")
doc = nlp(text)

print('Polarity:', doc._.polarity)

Polarity: -0.125

print('Sujectivity:', doc._.subjectivity)

Sujectivity: 0.9

print('Assessments:', doc._.assessments)

Assessments: [(['really', 'horrible'], -1.0, 1.0, None), (['worst', '!'], -1.0, 1.0, None), (['really', 'good'], 0.7, 0.6000000000000001, None), (['happy'], 0.8, 1.0, None)]

Using TextBlob:

from textblob import TextBlob
blob = TextBlob(text)

print(blob.sentiment_assessments.polarity)

-0.125

print(blob.sentiment_assessments.subjectivity)

0.9

print(blob.sentiment_assessments.assessments)

[(['really', 'horrible'], -1.0, 1.0, None), (['worst', '!'], -1.0, 1.0, None), (['really', 'good'], 0.7, 0.6000000000000001, None), (['happy'], 0.8, 1.0, None)]

Quick Reference

spaCyTextBlob performs sentiment analysis using the TextBlob library. Adding spaCyTextBlob to a spaCy nlp pipeline provides access to three new extension attributes.

• ._.polarity
• ._.subjectivity
• ._.assessments

These extension attributes can be accessed at the Doc, Span, or Token level.

Polarity is a float within the range [-1.0, 1.0], subjectivity is a float within the range [0.0, 1.0] where 0.0 is very objective and 1.0 is very subjective, and assessments is a list of polarity and subjectivity scores for the assessed tokens.

Reference and Attribution

• TextBlob
  • https://github.com/sloria/TextBlob
  • https://textblob.readthedocs.io/en/latest/
• negspaCy (for inpiration in writing pipeline and organizing repo)
  • https://github.com/jenojp/negspacy
• spaCy custom components
  • https://spacy.io/usage/processing-pipelines#custom-components