Textblob Polarity

High-Level Intuition

Measures the polarity i.e. how positive or negative a message is

Citation

Cao, et al. (2020)

Implementation Basics

To calculate polarity, we use the TextBlob Library in Python. This library is implemented using the Naive Bayes Algorithm, Textblob which is a “Bag of Words”-based classifier.

Implementation Notes/Caveats

This function uses a “Bag of Words”-based classifier, which is a naive way of measuring polarity.

For example, in the sentence “Everything in this restaurant was anything but lovely, amazing, wonderful, great!”, the sentence actually has a negative meaning as it means that nothing in the restaurant was good. However, the algorithm will classify it as a positive sentence because it simply counts the number of positive and negative words (4 positive words in this case make the sentence positive for the algorithm).

Interpreting the Feature

Scores are a continuous variable, ranging from -1 (extremely negative) to 1 (extremely positive)

Related Features

This feature is one of several that measure sentiment. Other sentiment-related features include Sentiment (RoBERTa); Negative_Emotion and Positive_Emotion, which are attributes of Politeness/Receptiveness Markers; and LIWC (a relevant column name being positive_affect_lexical_per_100).