Python Text Mining by George Alexandra;

Author:George, Alexandra; [George, Alexandra]
Language: eng
Format: epub, pdf
Publisher: BPB Publications
Published: 2022-07-15T00:00:00+00:00

Figure 5.11: Classification report of our review data

The results are more or less equal to that of the Opinion Lexicon results but the technique of Opinion Mining (Sentiment Analysis) is much better as it also gives a trade-off between subjective and objective and positive and negative.

TextBlob

We saw a lexicon model SentiWordNet which provided a Subjective to Objective trade-off. TextBlob also provides Subjectivity lexicon for English adjectives. The polarity are -1.0 (negative) - 1.0 (Positive) and subjectivity polarity +0.0 (Objective) –+1.0 (Subjective). This also makes use of synsets from WordNet and the version is WordNet3.

Each adjective is tagged as per sense, for example: (as given in the GitHub original documentation https://github.com/sloria/TextBlob/blob/dev/textblob/en/en-sentiment.xml)

Ridiculous (pitiful) = negative

Ridiculous (humorous) = positive

Let us take the example:

Consider the sentence: "I love it."

The polarity for this sentence as per textblob is:

textblob.TextBlob("I love it").sentiment.polarity

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.