Connectors Reference

Text Analytics

Microsoft Cognitive Services Text Analytics detects language, sentiment and more of the text you provide.

 

Status: Preview

Tier: Standard

Version: v2.0

 

Actions:

Name

Summary

KeyPhrases (MultiLanguageInput input)

Key Phrases

DetectLanguage (LanguageInput input, [advanced][Optional]integer numberOfLanguagesToDetect)

Detect Language

DetectSentiment (MultiLanguageInput input)

Detect Sentiment

TestConnection ()

Test Connection

 

Triggers:

Name

Summary

 

Objects:

Name

Summary

DetectedLanguageV2

 

KeyPhraseResult

 

LanguageInput

 

LanguageResult

 

MultiLanguageInput

 

SentimentResult

 

 

Actions:

KeyPhrases

Summary: Key Phrases

Description: Returns a list of strings denoting the key talking points in the input text. Currently, the following languages are supported: English, German, Spanish and Japanese.

 

Syntax:

TextAnalytics.KeyPhrases (MultiLanguageInput input)

 

Parameters:

Name

Type

Summary

Required

Related Action

input

MultiLanguageInput

 

 

True

 

Returns:

          Type:KeyPhraseResult

 

DetectLanguage

Summary: Detect Language

Description: Returns the detected language and a numeric score between 0 and 1. Scores close to 1 indicate 100% certainty that the identified language is true. A total of 120 languages are supported.

 

Syntax:

TextAnalytics.DetectLanguage (LanguageInput input, [advanced][Optional]integer numberOfLanguagesToDetect)

 

Parameters:

Name

Type

Summary

Required

Related Action

input

LanguageInput

 

 

True

numberOfLanguagesToDetect

integer(int32)

(Number of languages)

The number of languages to detect. Set to 1 by default.

False

 

Returns:

          Type:LanguageResult

 

DetectSentiment

Summary: Detect Sentiment

Description: Returns a numeric score between 0 and 1. Scores close to 1 indicate positive sentiment, while scores close to 0 indicate negative sentiment. Currently, the following languages are supported: English, Spanish, French, Portuguese.

 

Syntax:

TextAnalytics.DetectSentiment (MultiLanguageInput input)

 

Parameters:

Name

Type

Summary

Required

Related Action

input

MultiLanguageInput

 

 

True

 

Returns:

          Type:SentimentResult

 

TestConnection

Summary: Test Connection

Description: Tests the connection

 

Syntax:

TextAnalytics.TestConnection ()

 

Returns:

 


 

DetectedLanguageV2

Summary:

Description:

 

          Properties:

Name

Type

Summary

name

string

Name

The long name of a detected language (e.g. English, French).

iso6391Name

string

Language Code

A two letter representation of the detected language according to the ISO 639-1 standard (e.g. en, fr).

score

number(double)

Score

A confidence score between 0 and 1. Scores close to 1 indicate 100% certainty that the identified language is true.


 

KeyPhraseResult

Summary:

Description:

 

          Properties:

Name

Type

Summary

keyPhrases

array of (string)

Key Phrases

A list of representative words or phrases. The number of key phrases returned is proportional to the number of words in the input document.

id

string

Id

The unique document identifier.


 

LanguageInput

Summary:

Description:

 

          Properties:

Name

Type

Summary

text

string

Text

The text to analyze.


 

LanguageResult

Summary:

Description:

 

          Properties:

Name

Type

Summary

id

string

Id

The unique document identifier.

detectedLanguages

array of (DetectedLanguageV2)

 

A list of extracted languages.


 

MultiLanguageInput

Summary:

Description:

 

          Properties:

Name

Type

Summary

text

string

Text

The text to analyze.

language

string

Language

This is the 2 letter ISO 639-1 representation of a language.             For example, use "en" for English; "es" for Spanish etc.,  Values: [en, es, de, ja]


 

SentimentResult

Summary:

Description:

 

          Properties:

Name

Type

Summary

score

number(double)

Score

A decimal number between 0 and 1 denoting the sentiment of the document.  A score above 0.7 usually refers to a positive document while a score below 0.3 normally has a negative connotation. Mid values refer to neutral text.

id

string

Request ID

The unique document identifier.