WOLFRAM

Wolfram Language & System Documentation Center

"Sentiment" (Built-in Classifier)

Determine the sentiment of a text from a snippet.

Classes

Details

  • This classifier attempts to infer the sentiment that a snippet of text conveys.
  • The input text should typically be one or a few sentences.
  • This classifier assumes the text conveys only one sentiment. The probabilities reflect the belief in these sentiments, not the proportion of sentiments.
  • The current version only works for the English language.

Examples

open all close all

Basic Examples  (2)

Use the "Sentiment" built-in classifier to infer the sentiment of a review:

Wolfram Language code: Classify["Sentiment", "I enjoy working in this company"]

Classify multiple examples:

Wolfram Language code: Classify["Sentiment", {"I am so sad", "My phone broke again", "I love this movie"}]

Obtain the probabilities for the possible classes:

Wolfram Language code: Classify["Sentiment", "There is nothing good about the fellas in this movie", "Probabilities"]

Obtain a ClassifierFunction for this classifier:

Wolfram Language code: c = Classify["Sentiment"]

Apply the classifier to a list of examples:

Wolfram Language code: c[{"I love this movie", "I am so sad", "My phone broke again"}]

Scope  (1)

Load the ClassifierFunction corresponding to the built-in classifier:

Wolfram Language code: c = Classify["Sentiment"]

Obtain the possible classes:

Wolfram Language code: Information[c, "Classes"]

Options  (2)

ClassPriors  (1)

Use a custom ClassPriors to restrict the possible outputs:

Wolfram Language code: Classify["Sentiment", "There is nothing good about the fellas in this movie", ClassPriors -> <|"Negative" -> 0.5, "Neutral" -> 0.5|>]

IndeterminateThreshold  (1)

Use a custom IndeterminateThreshold:

Wolfram Language code: Classify["Sentiment", "There is nothing good about the fellas in this movie", IndeterminateThreshold -> 0.7]