Hands-On Machine Learning for Algorithmic Trading

Sentiment polarity and subjectivity

TextBlob provides polarity and subjectivity estimates for parsed documents using dictionaries provided by the Pattern library. These dictionaries map adjectives frequently found in product reviews to sentiment polarity scores, ranging from -1 to +1 (negative ↔ positive) and a similar subjectivity score (objective ↔ subjective).

The .sentiment attribute provides the average for each over the relevant tokens, whereas the .sentiment_assessments attribute lists the underlying values for each token (see notebook):

parsed_body.sentimentSentiment(polarity=0.088031914893617, subjectivity=0.46456433637284694)