AWS CLI version 2, the latest major version of AWS CLI, is now stable and recommended for general use. To view this page for the AWS CLI version 2, click here. For more information see the AWS CLI version 2 installation instructions and migration guide.
[ aws . comprehend ]
Inspects a batch of documents and returns a sentiment analysis for each entity identified in the documents.
For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide .
See also: AWS API Documentation
batch-detect-targeted-sentiment
--text-list <value>
--language-code <value>
[--cli-input-json <value>]
[--generate-cli-skeleton <value>]
[--debug]
[--endpoint-url <value>]
[--no-verify-ssl]
[--no-paginate]
[--output <value>]
[--query <value>]
[--profile <value>]
[--region <value>]
[--version <value>]
[--color <value>]
[--no-sign-request]
[--ca-bundle <value>]
[--cli-read-timeout <value>]
[--cli-connect-timeout <value>]
--text-list
(list)
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.
(string)
Syntax:
"string" "string" ...
--language-code
(string)
The language of the input documents. Currently, English is the only supported language.
Possible values:
en
es
fr
de
it
pt
ar
hi
ja
ko
zh
zh-TW
--cli-input-json
(string)
Performs service operation based on the JSON string provided. The JSON string follows the format provided by --generate-cli-skeleton
. If other arguments are provided on the command line, the CLI values will override the JSON-provided values. It is not possible to pass arbitrary binary values using a JSON-provided value as the string will be taken literally.
--generate-cli-skeleton
(string)
Prints a JSON skeleton to standard output without sending an API request. If provided with no value or the value input
, prints a sample input JSON that can be used as an argument for --cli-input-json
. If provided with the value output
, it validates the command inputs and returns a sample output JSON for that command.
--debug
(boolean)
Turn on debug logging.
--endpoint-url
(string)
Override command's default URL with the given URL.
--no-verify-ssl
(boolean)
By default, the AWS CLI uses SSL when communicating with AWS services. For each SSL connection, the AWS CLI will verify SSL certificates. This option overrides the default behavior of verifying SSL certificates.
--no-paginate
(boolean)
Disable automatic pagination. If automatic pagination is disabled, the AWS CLI will only make one call, for the first page of results.
--output
(string)
The formatting style for command output.
--query
(string)
A JMESPath query to use in filtering the response data.
--profile
(string)
Use a specific profile from your credential file.
--region
(string)
The region to use. Overrides config/env settings.
--version
(string)
Display the version of this tool.
--color
(string)
Turn on/off color output.
--no-sign-request
(boolean)
Do not sign requests. Credentials will not be loaded if this argument is provided.
--ca-bundle
(string)
The CA certificate bundle to use when verifying SSL certificates. Overrides config/env settings.
--cli-read-timeout
(int)
The maximum socket read time in seconds. If the value is set to 0, the socket read will be blocking and not timeout. The default value is 60 seconds.
--cli-connect-timeout
(int)
The maximum socket connect time in seconds. If the value is set to 0, the socket connect will be blocking and not timeout. The default value is 60 seconds.
To use the following examples, you must have the AWS CLI installed and configured. See the Getting started guide in the AWS CLI User Guide for more information.
Unless otherwise stated, all examples have unix-like quotation rules. These examples will need to be adapted to your terminal's quoting rules. See Using quotation marks with strings in the AWS CLI User Guide .
To detect the sentiment and each named entity for multiple input texts
The following batch-detect-targeted-sentiment
example analyzes multiple input texts and returns the named entities along with the prevailing sentiment attached to each entity. The pre-trained model's confidence score is also output for each prediction.
aws comprehend batch-detect-targeted-sentiment \
--language-code en \
--text-list "That movie was really boring, the original was way more entertaining" "The trail is extra beautiful today." "My meal was just okay."
Output:
{
"ResultList": [
{
"Index": 0,
"Entities": [
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"Score": 0.9999009966850281,
"GroupScore": 1.0,
"Text": "movie",
"Type": "MOVIE",
"MentionSentiment": {
"Sentiment": "NEGATIVE",
"SentimentScore": {
"Positive": 0.13887299597263336,
"Negative": 0.8057460188865662,
"Neutral": 0.05525200068950653,
"Mixed": 0.00012799999967683107
}
},
"BeginOffset": 5,
"EndOffset": 10
}
]
},
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"Score": 0.9921110272407532,
"GroupScore": 1.0,
"Text": "original",
"Type": "MOVIE",
"MentionSentiment": {
"Sentiment": "POSITIVE",
"SentimentScore": {
"Positive": 0.9999989867210388,
"Negative": 9.999999974752427e-07,
"Neutral": 0.0,
"Mixed": 0.0
}
},
"BeginOffset": 34,
"EndOffset": 42
}
]
}
]
},
{
"Index": 1,
"Entities": [
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"Score": 0.7545599937438965,
"GroupScore": 1.0,
"Text": "trail",
"Type": "OTHER",
"MentionSentiment": {
"Sentiment": "POSITIVE",
"SentimentScore": {
"Positive": 1.0,
"Negative": 0.0,
"Neutral": 0.0,
"Mixed": 0.0
}
},
"BeginOffset": 4,
"EndOffset": 9
}
]
},
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"Score": 0.9999960064888,
"GroupScore": 1.0,
"Text": "today",
"Type": "DATE",
"MentionSentiment": {
"Sentiment": "NEUTRAL",
"SentimentScore": {
"Positive": 9.000000318337698e-06,
"Negative": 1.9999999949504854e-06,
"Neutral": 0.9999859929084778,
"Mixed": 3.999999989900971e-06
}
},
"BeginOffset": 29,
"EndOffset": 34
}
]
}
]
},
{
"Index": 2,
"Entities": [
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"Score": 0.9999880194664001,
"GroupScore": 1.0,
"Text": "My",
"Type": "PERSON",
"MentionSentiment": {
"Sentiment": "NEUTRAL",
"SentimentScore": {
"Positive": 0.0,
"Negative": 0.0,
"Neutral": 1.0,
"Mixed": 0.0
}
},
"BeginOffset": 0,
"EndOffset": 2
}
]
},
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"Score": 0.9995260238647461,
"GroupScore": 1.0,
"Text": "meal",
"Type": "OTHER",
"MentionSentiment": {
"Sentiment": "NEUTRAL",
"SentimentScore": {
"Positive": 0.04695599898695946,
"Negative": 0.003226999891921878,
"Neutral": 0.6091709733009338,
"Mixed": 0.34064599871635437
}
},
"BeginOffset": 3,
"EndOffset": 7
}
]
}
]
}
],
"ErrorList": []
}
For more information, see Targeted Sentiment in the Amazon Comprehend Developer Guide.
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, theResultList
is empty.(structure)
Analysis results for one of the documents in the batch.
Index -> (integer)
The zero-based index of this result in the input list.Entities -> (list)
An array of targeted sentiment entities.
(structure)
Information about one of the entities found by targeted sentiment analysis.
For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide .
DescriptiveMentionIndex -> (list)
One or more index into the Mentions array that provides the best name for the entity group.
(integer)
Mentions -> (list)
An array of mentions of the entity in the document. The array represents a co-reference group. See Co-reference group for an example.
(structure)
Information about one mention of an entity. The mention information includes the location of the mention in the text and the sentiment of the mention.
For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide .
Score -> (float)
Model confidence that the entity is relevant. Value range is zero to one, where one is highest confidence.GroupScore -> (float)
The confidence that all the entities mentioned in the group relate to the same entity.Text -> (string)
The text in the document that identifies the entity.Type -> (string)
The type of the entity. Amazon Comprehend supports a variety of entity types .MentionSentiment -> (structure)
Contains the sentiment and sentiment score for the mention.
Sentiment -> (string)
The sentiment of the mention.SentimentScore -> (structure)
Describes the level of confidence that Amazon Comprehend has in the accuracy of its detection of sentiments.
Positive -> (float)
The level of confidence that Amazon Comprehend has in the accuracy of its detection of thePOSITIVE
sentiment.Negative -> (float)
The level of confidence that Amazon Comprehend has in the accuracy of its detection of theNEGATIVE
sentiment.Neutral -> (float)
The level of confidence that Amazon Comprehend has in the accuracy of its detection of theNEUTRAL
sentiment.Mixed -> (float)
The level of confidence that Amazon Comprehend has in the accuracy of its detection of theMIXED
sentiment.BeginOffset -> (integer)
The offset into the document text where the mention begins.EndOffset -> (integer)
The offset into the document text where the mention ends.
ErrorList -> (list)
List of errors that the operation can return.
(structure)
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.