Real-time analysis using the API
The following examples demonstrate how to use Amazon Comprehend API for real-time analysis, using the AWS CLI, and the AWS SDKs for .NET, Java, and Python. Use the examples to learn about the Amazon Comprehend synchronous operations and as building blocks for your own applications.
The .NET examples in this section use the AWS SDK for .NET. You can use the AWS Toolkit for Visual Studio to develop AWS applications using .NET. It includes helpful templates and the AWS Explorer for deploying applications and managing services. For a .NET developer perspective of AWS, see the AWS guide for .NET developers.
Topics
Detecting the dominant language
To determine the dominant language used in text, use the DetectDominantLanguage operation. To detect the dominant language in up to 25 documents in a batch, use the BatchDetectDominantLanguage operation. For more information, see Real-time batch APIs.
Topics
Using the AWS Command Line Interface
The following example demonstrates using the DetectDominantLanguage
operation with the AWS CLI.
The example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
aws comprehend detect-dominant-language \ --regionregion\ --text "It is raining today in Seattle."
Amazon Comprehend responds with the following:
{ "Languages": [ { "LanguageCode": "en", "Score": 0.9793661236763 } ] }
Using the AWS SDK for Java, SDK for Python, or AWS SDK for .NET
For SDK examples of how to determine the dominant language, see Detect the dominant language in a document with Amazon Comprehend using an AWS SDK.
Detecting named entities
To determine the named entities in a document, use the DetectEntities operation. To detect entities in up to 25 documents in a batch, use the BatchDetectEntities operation. For more information, see Real-time batch APIs.
Topics
Using the AWS Command Line Interface
The following example demonstrates using the DetectEntities operation
using the AWS CLI. You must specify the language of the input text.
The example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
aws comprehend detect-entities \ --regionregion\ --language-code "en" \ --text "It is raining today in Seattle."
Amazon Comprehend responds with the following:
{ "Entities": [ { "Text": "today", "Score": 0.97, "Type": "DATE", "BeginOffset": 14, "EndOffset": 19 }, { "Text": "Seattle", "Score": 0.95, "Type": "LOCATION", "BeginOffset": 23, "EndOffset": 30 } ], "LanguageCode": "en" }
Using the AWS SDK for Java, SDK for Python, or AWS SDK for .NET
For SDK examples of how to determine the dominant language, see Detect entities in a document with Amazon Comprehend using an AWS SDK.
Detecting key phrases
To determine the key noun phrases used in text, use the DetectKeyPhrases operation. To detect the key noun phrases in up to 25 documents in a batch, use the BatchDetectKeyPhrases operation. For more information, see Real-time batch APIs.
Topics
Using the AWS Command Line Interface
The following example demonstrates using the DetectKeyPhrases
operation with the AWS CLI. You must specify the language of the input text.
The example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
aws comprehend detect-key-phrases \ --regionregion\ --language-code "en" \ --text "It is raining today in Seattle."
Amazon Comprehend responds with the following:
{ "LanguageCode": "en", "KeyPhrases": [ { "Text": "today", "Score": 0.89, "BeginOffset": 14, "EndOffset": 19 }, { "Text": "Seattle", "Score": 0.91, "BeginOffset": 23, "EndOffset": 30 } ] }
Using the AWS SDK for Java, SDK for Python, or AWS SDK for .NET
For SDK examples that detect key phrases, see Detect key phrases in a document with Amazon Comprehend using an AWS SDK.
Determining sentiment
Amazon Comprehend provides the following API operations for analyzing sentiment:
DetectSentiment – Determines the overall emotional sentiment of a document.
-
BatchDetectSentiment – Determine the overall sentiment in up to 25 documents in a batch. For more information, see Real-time batch APIs
StartSentimentDetectionJob – Starts an asynchronous sentiment detection job for a collection of documents.
ListSentimentDetectionJobs – Returns the list of sentiment detection jobs that you have submitted.
DescribeSentimentDetectionJob – Gets the properties (including status) associated with the specified sentiment detection job.
StopSentimentDetectionJob – Stops the specified in-progress sentiment job.
Topics
Using the AWS Command Line Interface
The following example demonstrates using the DetectSentiment
operation with the AWS CLI. This example specifies the language of the input
text.
The example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
aws comprehend detect-sentiment \ --regionregion\ --language-code "en" \ --text "It is raining today in Seattle."
Amazon Comprehend responds with the following:
{
"SentimentScore": {
"Mixed": 0.014585512690246105,
"Positive": 0.31592071056365967,
"Neutral": 0.5985543131828308,
"Negative": 0.07093945890665054
},
"Sentiment": "NEUTRAL",
"LanguageCode": "en"
}
Using the AWS SDK for Java, SDK for Python, or AWS SDK for .NET
For SDK examples that determine the sentiment of input text, see Detect the sentiment of a document with Amazon Comprehend using an AWS SDK.
Real-time analysis for targeted sentiment
Amazon Comprehend provides the following API operations for targeted sentiment real-time analysis:
DetectTargetedSentiment – Analyzes sentiment of the entities mentioned in a document.
-
BatchDetectTargetedSentiment – Analyzes targeted sentiment for up to 25 documents in a batch. For more information, see Real-time batch APIs
If the text you are analyzing doesn't include any targeted sentiment Entity types, the API returns an empty Entities array.
Using the AWS Command Line Interface
The following example demonstrates using the DetectTargetedSentiment
operation with the AWS CLI. This example specifies the language of the input
text.
The example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
aws comprehend detect-targeted-sentiment \ --regionregion\ --language-code "en" \ --text "The burger was cooked perfectly but it was cold. The service was OK."
Amazon Comprehend responds with the following:
{
"Entities": [
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"BeginOffset": 4,
"EndOffset": 10,
"Score": 1,
"GroupScore": 1,
"Text": "burger",
"Type": "OTHER",
"MentionSentiment": {
"Sentiment": "POSITIVE",
"SentimentScore": {
"Mixed": 0.001515,
"Negative": 0.000822,
"Neutral": 0.000243,
"Positive": 0.99742
}
}
},
{
"BeginOffset": 36,
"EndOffset": 38,
"Score": 0.999843,
"GroupScore": 0.999661,
"Text": "it",
"Type": "OTHER",
"MentionSentiment": {
"Sentiment": "NEGATIVE",
"SentimentScore": {
"Mixed": 0,
"Negative": 0.999996,
"Neutral": 0.000004,
"Positive": 0
}
}
}
]
},
{
"DescriptiveMentionIndex": [
0
],
"Mentions": [
{
"BeginOffset": 53,
"EndOffset": 60,
"Score": 1,
"GroupScore": 1,
"Text": "service",
"Type": "ATTRIBUTE",
"MentionSentiment": {
"Sentiment": "NEUTRAL",
"SentimentScore": {
"Mixed": 0.000033,
"Negative": 0.000089,
"Neutral": 0.993325,
"Positive": 0.006553
}
}
}
]
}
]
}
Detecting syntax
To parse text to extract the individual words and determine the parts of speech for each word, use the DetectSyntax operation. To parse the syntax of up to 25 documents in a batch, use the BatchDetectSyntax operation. For more information, see Real-time batch APIs.
Topics
Using the AWS Command Line Interface.
The following example demonstrates using the DetectSyntax operation
with the AWS CLI. This example specifies the language of the input text.
The example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
aws comprehend detect-syntax \ --regionregion\ --language-code "en" \ --text "It is raining today in Seattle."
Amazon Comprehend responds with the following:
{ "SyntaxTokens": [ { "Text": "It", "EndOffset": 2, "BeginOffset": 0, "PartOfSpeech": { "Tag": "PRON", "Score": 0.8389829397201538 }, "TokenId": 1 }, { "Text": "is", "EndOffset": 5, "BeginOffset": 3, "PartOfSpeech": { "Tag": "AUX", "Score": 0.9189288020133972 }, "TokenId": 2 }, { "Text": "raining", "EndOffset": 13, "BeginOffset": 6, "PartOfSpeech": { "Tag": "VERB", "Score": 0.9977611303329468 }, "TokenId": 3 }, { "Text": "today", "EndOffset": 19, "BeginOffset": 14, "PartOfSpeech": { "Tag": "NOUN", "Score": 0.9993606209754944 }, "TokenId": 4 }, { "Text": "in", "EndOffset": 22, "BeginOffset": 20, "PartOfSpeech": { "Tag": "ADP", "Score": 0.9999061822891235 }, "TokenId": 5 }, { "Text": "Seattle", "EndOffset": 30, "BeginOffset": 23, "PartOfSpeech": { "Tag": "PROPN", "Score": 0.9940338730812073 }, "TokenId": 6 }, { "Text": ".", "EndOffset": 31, "BeginOffset": 30, "PartOfSpeech": { "Tag": "PUNCT", "Score": 0.9999997615814209 }, "TokenId": 7 } ] }
Using the AWS SDK for Java, SDK for Python, or AWS SDK for .NET
For SDK examples that detect the syntax of input text, see Detect syntactial elements of a document with Amazon Comprehend using an AWS SDK.
Real-time batch APIs
To send batches of up to 25 documents, you can use the Amazon Comprehend real-time batch operations. Calling a batch operation is identical to calling the single document APIs for each document in the request. Using the batch APIs can result in better performance for your applications. For more information, see Multiple document synchronous processing.
Batch processing with the AWS CLI
These examples show how to use the batch API operations using the AWS Command Line Interface. All
of the operations except BatchDetectDominantLanguage use the following
JSON file called process.json as input. For that operation the
LanguageCode entity is not included.
The third document in the JSON file ("$$$$$$$$") will cause an error
during batch processing. It is included so that the operations will include an BatchItemError in the
response.
{ "LanguageCode": "en", "TextList": [ "I have been living in Seattle for almost 4 years", "It is raining today in Seattle", "$$$$$$$$" ] }
The examples are formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).
Topics
Detect the dominant language using a batch (AWS CLI)
The BatchDetectDominantLanguage operation determines the
dominant language of each document in a batch. For a list of the languages that
Amazon Comprehend can detect, see Dominant language. The following AWS CLI command calls the
BatchDetectDominantLanguage operation.
aws comprehend batch-detect-dominant-language \ --endpointendpoint\ --regionregion\ --cli-input-json file://path to input file/process.json
The following is the response from the
BatchDetectDominantLanguage operation:
{ "ResultList": [ { "Index": 0, "Languages":[ { "LanguageCode":"en", "Score": 0.99 } ] }, { "Index": 1 "Languages":[ { "LanguageCode":"en", "Score": 0.82 } ] } ], "ErrorList": [ { "Index": 2, "ErrorCode": "InternalServerException", "ErrorMessage": "Unexpected Server Error. Please try again." } ] }
Detect entities using a batch (AWS CLI)
Use the BatchDetectEntities operation to find the entities
present in a batch of documents. For more information about entities, see Entities. The following AWS CLI
command calls the BatchDetectEntities operation.
aws comprehend batch-detect-entities \ --endpointendpoint\ --regionregion\ --cli-input-json file://path to input file/process.json
Detect key phrases using a batch (AWS CLI)
The BatchDetectKeyPhrases operation returns the key noun
phrases in a batch of documents. The following AWS CLI command calls the
BatchDetectKeyNounPhrases operation.
aws comprehend batch-detect-key-phrases --endpointendpoint--regionregion--cli-input-json file://path to input file/process.json
Detect sentiment using a batch (AWS CLI)
Detect the overall sentiment of a batch of documents using the BatchDetectSentiment
operation. The following AWS CLI command calls the
BatchDetectSentiment operation.
aws comprehend batch-detect-sentiment \ --endpointendpoint\ --regionregion\ --cli-input-json file://path to input file/process.json
Batch processing with the AWS SDK for .NET
The following sample program shows how to use the BatchDetectEntities operation with the AWS SDK for .NET. The response from the server contains a BatchDetectEntitiesItemResult object for each document that was successfully processed. If there is an error processing a document, there will be a record in the error list in the response. The example gets each of the documents with an error and resends them.
The .NET example in this section uses the AWS SDK for .NET. You can use the AWS Toolkit for Visual Studio to develop AWS applications using .NET. It includes helpful templates and the AWS Explorer for deploying applications and managing services. For a .NET developer perspective of AWS, see the AWS guide for .NET developers.
using System; using System.Collections.Generic; using Amazon.Comprehend; using Amazon.Comprehend.Model; namespace Comprehend { class Program { // Helper method for printing properties static private void PrintEntity(Entity entity) { Console.WriteLine(" Text: {0}, Type: {1}, Score: {2}, BeginOffset: {3} EndOffset: {4}", entity.Text, entity.Type, entity.Score, entity.BeginOffset, entity.EndOffset); } static void Main(string[] args) { AmazonComprehendClient comprehendClient = new AmazonComprehendClient(Amazon.RegionEndpoint.USWest2); List<String> textList = new List<String>() { { "I love Seattle" }, { "Today is Sunday" }, { "Tomorrow is Monday" }, { "I love Seattle" } }; // Call detectEntities API Console.WriteLine("Calling BatchDetectEntities"); BatchDetectEntitiesRequest batchDetectEntitiesRequest = new BatchDetectEntitiesRequest() { TextList = textList, LanguageCode = "en" }; BatchDetectEntitiesResponse batchDetectEntitiesResponse = comprehendClient.BatchDetectEntities(batchDetectEntitiesRequest); foreach (BatchDetectEntitiesItemResult item in batchDetectEntitiesResponse.ResultList) { Console.WriteLine("Entities in {0}:", textList[item.Index]); foreach (Entity entity in item.Entities) PrintEntity(entity); } // check if we need to retry failed requests if (batchDetectEntitiesResponse.ErrorList.Count != 0) { Console.WriteLine("Retrying Failed Requests"); List<String> textToRetry = new List<String>(); foreach(BatchItemError errorItem in batchDetectEntitiesResponse.ErrorList) textToRetry.Add(textList[errorItem.Index]); batchDetectEntitiesRequest = new BatchDetectEntitiesRequest() { TextList = textToRetry, LanguageCode = "en" }; batchDetectEntitiesResponse = comprehendClient.BatchDetectEntities(batchDetectEntitiesRequest); foreach(BatchDetectEntitiesItemResult item in batchDetectEntitiesResponse.ResultList) { Console.WriteLine("Entities in {0}:", textList[item.Index]); foreach (Entity entity in item.Entities) PrintEntity(entity); } } Console.WriteLine("End of DetectEntities"); } } }
