batch_detect_sentiment

batch_detect_sentiment(**kwargs)

Inspects a batch of documents and returns an inference of the prevailing sentiment, POSITIVE , NEUTRAL , MIXED , or NEGATIVE , in each one.

See also: AWS API Documentation

Request Syntax

response = client.batch_detect_sentiment(
    TextList=[
        'string',
    ],
    LanguageCode='en'|'es'|'fr'|'de'|'it'|'pt'|'ar'|'hi'|'ja'|'ko'|'zh'|'zh-TW'
)
Parameters
  • TextList (list) --

    [REQUIRED]

    A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.

    Note

    Amazon Comprehend performs real-time sentiment analysis on the first 500 characters of the input text and ignores any additional text in the input.

    • (string) --
  • LanguageCode (string) --

    [REQUIRED]

    The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.

Return type

dict

Returns

Response Syntax

{
    'ResultList': [
        {
            'Index': 123,
            'Sentiment': 'POSITIVE'|'NEGATIVE'|'NEUTRAL'|'MIXED',
            'SentimentScore': {
                'Positive': ...,
                'Negative': ...,
                'Neutral': ...,
                'Mixed': ...
            }
        },
    ],
    'ErrorList': [
        {
            'Index': 123,
            'ErrorCode': 'string',
            'ErrorMessage': 'string'
        },
    ]
}

Response Structure

  • (dict) --

    • ResultList (list) --

      A list of objects containing the results of the operation. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If all of the documents contain an error, the ResultList is empty.

      • (dict) --

        The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.

        • Index (integer) --

          The zero-based index of the document in the input list.

        • Sentiment (string) --

          The sentiment detected in the document.

        • SentimentScore (dict) --

          The level of confidence that Amazon Comprehend has in the accuracy of its sentiment detection.

          • Positive (float) --

            The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.

          • Negative (float) --

            The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.

          • Neutral (float) --

            The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.

          • Mixed (float) --

            The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.

    • ErrorList (list) --

      A list containing one object for each document that contained an error. The results are sorted in ascending order by the Index field and match the order of the documents in the input list. If there are no errors in the batch, the ErrorList is empty.

      • (dict) --

        Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.

        • Index (integer) --

          The zero-based index of the document in the input list.

        • ErrorCode (string) --

          The numeric error code of the error.

        • ErrorMessage (string) --

          A text description of the error.

Exceptions

  • Comprehend.Client.exceptions.InvalidRequestException
  • Comprehend.Client.exceptions.TextSizeLimitExceededException
  • Comprehend.Client.exceptions.UnsupportedLanguageException
  • Comprehend.Client.exceptions.BatchSizeLimitExceededException
  • Comprehend.Client.exceptions.InternalServerException