spacytextblob
A TextBlob sentiment analysis pipeline component for spaCy.
Install
Install spacytextblob from PyPi.
TextBlob requires additional data to be downloaded before getting started.
spaCy also requires that you download a model to get started.
Quick Start
spacytextblob allows you to access all of the attributes created of the textblob.TextBlob
class but within the spaCy framework. The code below will demonstrate how to use spacytextblob on a simple string.
import spacy
from spacytextblob.spacytextblob import SpacyTextBlob
nlp = spacy.load('en_core_web_sm')
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."
nlp.add_pipe("spacytextblob")
doc = nlp(text)
print(doc._.blob.polarity)
# -0.125
print(doc._.blob.subjectivity)
# 0.9
print(doc._.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)]
In comparison, here is how the same code would look using TextBlob
:
from textblob import TextBlob
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."
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 creates a new extension attribute for the Doc
, Span
, and Token
classes from spaCy.
Doc._.blob
Span._.blob
Token._.blob
The ._.blob
attribute contains all of the methods and attributes that belong to the textblob.TextBlob
class Some of the common methods and attributes include:
._.blob.polarity
: a float within the range [-1.0, 1.0].._.blob.subjectivity
: a float within the range [0.0, 1.0] where 0.0 is very objective and 1.0 is very subjective.._.blob.sentiment_assessments.assessments
: a list of polarity and subjectivity scores for the assessed tokens.
See the textblob docs for the complete listing of all attributes and methods that are available in ._.blob
.
Reference and Attribution
- TextBlob
- negspaCy (for inspiration in writing pipeline and organizing repo)
- spaCy custom components