Analyzing Entity Sentiment

Entity Sentiment Analysis combines both entity analysis and sentiment analysis and attempts to determine the sentiment (positive or negative) expressed about entities within the text. Entity sentiment is represented by numerical score and magnitude values and is determined for each mention of an entity. Those scores are then aggregated into an overall sentiment score and magnitude for an entity. For information on how to interpret the score and magnitude sentiment values included in the analysis, see Interpreting sentiment analysis values.

The following examples show how to query the analyzeEntitySentiment method.

Analyzing Entity Sentiment

Here is an example of analyzing entity sentiment provided as a string:

Protocol

To analyze entity sentiment in a document, make a POST request to the documents:analyzeEntitySentiment REST method and provide the appropriate request body as shown in the following example.

The example uses the gcloud auth application-default print-access-token command to obtain an access token for a service account set up for the project using the Google Cloud Platform Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account see the Quickstart.

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'document':{
    'type':'PLAIN_TEXT',
    'content':'I love R&B music. Marvin Gaye is the best.
               \'What\'s Going On\' is one of my favorite songs.
               It was so sad when Marvin Gaye died.'
  },
  'encodingType':'UTF8'
}" "https://language.googleapis.com/v1/documents:analyzeEntitySentiment"

GCLOUD COMMAND

Refer to the analyze-entity-sentiment command for complete details.

To perform entity sentiment analysis, use the gcloud command line tool and use the --content flag to identify the content to analyze:

gcloud ml language analyze-entity-sentiment \
  --content="I love R&B music. Marvin Gaye is the best. 'What's Going On' is one of my favorite songs. It was so sad when Marvin Gaye died."

C#

private static void AnalyzeEntitySentimentFromText(string text)
{
    var client = LanguageServiceClient.Create();
    var response = client.AnalyzeEntitySentiment(new Document()
    {
        Content = text,
        Type = Document.Types.Type.PlainText
    });
    WriteEntitySentiment(response.Entities);
}

private static void WriteEntitySentiment(IEnumerable<Entity> entities)
{
    Console.WriteLine("Entity Sentiment:");
    foreach (var entity in entities)
    {
        Console.WriteLine($"\t{entity.Name} "
            + $"({(int)(entity.Salience * 100)}%)");
        Console.WriteLine($"\t\tScore: {entity.Sentiment.Score}");
        Console.WriteLine($"\t\tMagnitude { entity.Sentiment.Magnitude}");
    }
}

Go


func analyzeEntitySentiment(ctx context.Context, client *language.Client, text string) (*languagepb.AnalyzeEntitySentimentResponse, error) {
	return client.AnalyzeEntitySentiment(ctx, &languagepb.AnalyzeEntitySentimentRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_Content{
				Content: text,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
	})
}

Java

// Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  Document doc = Document.newBuilder()
      .setContent(text).setType(Type.PLAIN_TEXT).build();
  AnalyzeEntitySentimentRequest request = AnalyzeEntitySentimentRequest.newBuilder()
      .setDocument(doc)
      .setEncodingType(EncodingType.UTF16).build();
  // detect entity sentiments in the given string
  AnalyzeEntitySentimentResponse response = language.analyzeEntitySentiment(request);
  // Print the response
  for (Entity entity : response.getEntitiesList()) {
    System.out.printf("Entity: %s\n", entity.getName());
    System.out.printf("Salience: %.3f\n", entity.getSalience());
    System.out.printf("Sentiment : %s\n", entity.getSentiment());
    for (EntityMention mention : entity.getMentionsList()) {
      System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
      System.out.printf("Content: %s\n", mention.getText().getContent());
      System.out.printf("Magnitude: %.3f\n", mention.getSentiment().getMagnitude());
      System.out.printf("Sentiment score : %.3f\n", mention.getSentiment().getScore());
      System.out.printf("Type: %s\n\n", mention.getType());
    }
  }
}

Node.js

// Imports the Google Cloud client library
const language = require('@google-cloud/language');

// Creates a client
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following line to run this code.
 */
// const text = 'Your text to analyze, e.g. Hello, world!';

// Prepares a document, representing the provided text
const document = {
  content: text,
  type: 'PLAIN_TEXT',
};

// Detects sentiment of entities in the document
const [result] = await client.analyzeEntitySentiment({document});
const entities = result.entities;

console.log(`Entities and sentiments:`);
entities.forEach(entity => {
  console.log(`  Name: ${entity.name}`);
  console.log(`  Type: ${entity.type}`);
  console.log(`  Score: ${entity.sentiment.score}`);
  console.log(`  Magnitude: ${entity.sentiment.magnitude}`);
});

Python

from google.cloud import language_v1
from google.cloud.language_v1 import enums


def sample_analyze_entity_sentiment(text_content):
    """
    Analyzing Entity Sentiment in a String

    Args:
      text_content The text content to analyze
    """

    client = language_v1.LanguageServiceClient()

    # text_content = 'Grapes are good. Bananas are bad.'

    # Available types: PLAIN_TEXT, HTML
    type_ = enums.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language = "en"
    document = {"content": text_content, "type": type_, "language": language}

    # Available values: NONE, UTF8, UTF16, UTF32
    encoding_type = enums.EncodingType.UTF8

    response = client.analyze_entity_sentiment(document, encoding_type=encoding_type)
    # Loop through entitites returned from the API
    for entity in response.entities:
        print(u"Representative name for the entity: {}".format(entity.name))
        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al
        print(u"Entity type: {}".format(enums.Entity.Type(entity.type).name))
        # Get the salience score associated with the entity in the [0, 1.0] range
        print(u"Salience score: {}".format(entity.salience))
        # Get the aggregate sentiment expressed for this entity in the provided document.
        sentiment = entity.sentiment
        print(u"Entity sentiment score: {}".format(sentiment.score))
        print(u"Entity sentiment magnitude: {}".format(sentiment.magnitude))
        # Loop over the metadata associated with entity. For many known entities,
        # the metadata is a Wikipedia URL (wikipedia_url) and Knowledge Graph MID (mid).
        # Some entity types may have additional metadata, e.g. ADDRESS entities
        # may have metadata for the address street_name, postal_code, et al.
        for metadata_name, metadata_value in entity.metadata.items():
            print(u"{} = {}".format(metadata_name, metadata_value))

        # Loop over the mentions of this entity in the input document.
        # The API currently supports proper noun mentions.
        for mention in entity.mentions:
            print(u"Mention text: {}".format(mention.text.content))
            # Get the mention type, e.g. PROPER for proper noun
            print(
                u"Mention type: {}".format(enums.EntityMention.Type(mention.type).name)
            )

    # Get the language of the text, which will be the same as
    # the language specified in the request or, if not specified,
    # the automatically-detected language.
    print(u"Language of the text: {}".format(response.language))

PHP

use Google\Cloud\Language\V1\Document;
use Google\Cloud\Language\V1\Document\Type;
use Google\Cloud\Language\V1\LanguageServiceClient;
use Google\Cloud\Language\V1\Entity\Type as EntityType;

/** Uncomment and populate these variables in your code */
// $text = 'The text to analyze.';

$languageServiceClient = new LanguageServiceClient();
try {
    // Create a new Document, add text as content and set type to PLAIN_TEXT
    $document = (new Document())
        ->setContent($text)
        ->setType(Type::PLAIN_TEXT);

    // Call the analyzeEntitySentiment function
    $response = $languageServiceClient->analyzeEntitySentiment($document);
    $entities = $response->getEntities();
    // Print out information about each entity
    foreach ($entities as $entity) {
        printf('Entity Name: %s' . PHP_EOL, $entity->getName());
        printf('Entity Type: %s' . PHP_EOL, EntityType::name($entity->getType()));
        printf('Entity Salience: %s' . PHP_EOL, $entity->getSalience());
        $sentiment = $entity->getSentiment();
        if ($sentiment) {
            printf('Entity Magnitude: %s' . PHP_EOL, $sentiment->getMagnitude());
            printf('Entity Score: %s' . PHP_EOL, $sentiment->getScore());
        }
        print(PHP_EOL);
    }
} finally {
    $languageServiceClient->close();
}

Analyzing Entity Sentiment from Google Cloud Storage

Here is an example of analyzing entity sentiment stored in a text file on Google Cloud Storage:

Protocol

To analyze entity sentiment from a document stored in Google Cloud Storage, make a POST request to the documents:analyzeEntitySentiment REST method and provide the appropriate request body with the path to the document as shown in the following example.

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'document':{
    'type':'PLAIN_TEXT',
    'gcsContentUri':'gs://<bucket-name>/<object-name>'
  }
}" "https://language.googleapis.com/v1/documents:analyzeEntitySentiment"

GCLOUD COMMAND

Refer to the analyze-entity-sentiment command for complete details.

To perform entity sentiment analysis, use the gcloud command line tool and use the --content flag to identify the content to analyze:

gcloud ml language analyze-entity-sentiment \
  --content-file=gs://<bucket-name>/<object-name>

C#

private static void AnalyzeEntitySentimentFromFile(string gcsUri)
{
    var client = LanguageServiceClient.Create();
    var response = client.AnalyzeEntitySentiment(new Document()
    {
        GcsContentUri = gcsUri,
        Type = Document.Types.Type.PlainText
    });
    WriteEntitySentiment(response.Entities);
}
private static void WriteEntitySentiment(IEnumerable<Entity> entities)
{
    Console.WriteLine("Entity Sentiment:");
    foreach (var entity in entities)
    {
        Console.WriteLine($"\t{entity.Name} "
            + $"({(int)(entity.Salience * 100)}%)");
        Console.WriteLine($"\t\tScore: {entity.Sentiment.Score}");
        Console.WriteLine($"\t\tMagnitude { entity.Sentiment.Magnitude}");
    }
}

Java

// Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  Document doc = Document.newBuilder()
      .setGcsContentUri(gcsUri)
      .setType(Type.PLAIN_TEXT)
      .build();
  AnalyzeEntitySentimentRequest request = AnalyzeEntitySentimentRequest.newBuilder()
      .setDocument(doc)
      .setEncodingType(EncodingType.UTF16)
      .build();
  // Detect entity sentiments in the given file
  AnalyzeEntitySentimentResponse response = language.analyzeEntitySentiment(request);
  // Print the response
  for (Entity entity : response.getEntitiesList()) {
    System.out.printf("Entity: %s\n", entity.getName());
    System.out.printf("Salience: %.3f\n", entity.getSalience());
    System.out.printf("Sentiment : %s\n", entity.getSentiment());
    for (EntityMention mention : entity.getMentionsList()) {
      System.out.printf("Begin offset: %d\n", mention.getText().getBeginOffset());
      System.out.printf("Content: %s\n", mention.getText().getContent());
      System.out.printf("Magnitude: %.3f\n", mention.getSentiment().getMagnitude());
      System.out.printf("Sentiment score : %.3f\n", mention.getSentiment().getScore());
      System.out.printf("Type: %s\n\n", mention.getType());
    }
  }
}

Node.js

// Imports the Google Cloud client library
const language = require('@google-cloud/language');

// Creates a client
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following lines to run this code
 */
// const bucketName = 'Your bucket name, e.g. my-bucket';
// const fileName = 'Your file name, e.g. my-file.txt';

// Prepares a document, representing a text file in Cloud Storage
const document = {
  gcsContentUri: `gs://${bucketName}/${fileName}`,
  type: 'PLAIN_TEXT',
};

// Detects sentiment of entities in the document
const [result] = await client.analyzeEntitySentiment({document});
const entities = result.entities;

console.log(`Entities and sentiments:`);
entities.forEach(entity => {
  console.log(`  Name: ${entity.name}`);
  console.log(`  Type: ${entity.type}`);
  console.log(`  Score: ${entity.sentiment.score}`);
  console.log(`  Magnitude: ${entity.sentiment.magnitude}`);
});

Python

from google.cloud import language_v1
from google.cloud.language_v1 import enums


def sample_analyze_entity_sentiment(gcs_content_uri):
    """
    Analyzing Entity Sentiment in text file stored in Cloud Storage

    Args:
      gcs_content_uri Google Cloud Storage URI where the file content is located.
      e.g. gs://[Your Bucket]/[Path to File]
    """

    client = language_v1.LanguageServiceClient()

    # gcs_content_uri = 'gs://cloud-samples-data/language/entity-sentiment.txt'

    # Available types: PLAIN_TEXT, HTML
    type_ = enums.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language = "en"
    document = {"gcs_content_uri": gcs_content_uri, "type": type_, "language": language}

    # Available values: NONE, UTF8, UTF16, UTF32
    encoding_type = enums.EncodingType.UTF8

    response = client.analyze_entity_sentiment(document, encoding_type=encoding_type)
    # Loop through entitites returned from the API
    for entity in response.entities:
        print(u"Representative name for the entity: {}".format(entity.name))
        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al
        print(u"Entity type: {}".format(enums.Entity.Type(entity.type).name))
        # Get the salience score associated with the entity in the [0, 1.0] range
        print(u"Salience score: {}".format(entity.salience))
        # Get the aggregate sentiment expressed for this entity in the provided document.
        sentiment = entity.sentiment
        print(u"Entity sentiment score: {}".format(sentiment.score))
        print(u"Entity sentiment magnitude: {}".format(sentiment.magnitude))
        # Loop over the metadata associated with entity. For many known entities,
        # the metadata is a Wikipedia URL (wikipedia_url) and Knowledge Graph MID (mid).
        # Some entity types may have additional metadata, e.g. ADDRESS entities
        # may have metadata for the address street_name, postal_code, et al.
        for metadata_name, metadata_value in entity.metadata.items():
            print(u"{} = {}".format(metadata_name, metadata_value))

        # Loop over the mentions of this entity in the input document.
        # The API currently supports proper noun mentions.
        for mention in entity.mentions:
            print(u"Mention text: {}".format(mention.text.content))
            # Get the mention type, e.g. PROPER for proper noun
            print(
                u"Mention type: {}".format(enums.EntityMention.Type(mention.type).name)
            )

    # Get the language of the text, which will be the same as
    # the language specified in the request or, if not specified,
    # the automatically-detected language.
    print(u"Language of the text: {}".format(response.language))

PHP

use Google\Cloud\Language\V1\Document;
use Google\Cloud\Language\V1\Document\Type;
use Google\Cloud\Language\V1\LanguageServiceClient;
use Google\Cloud\Language\V1\Entity\Type as EntityType;

/** Uncomment and populate these variables in your code */
// $uri = 'The cloud storage object to analyze (gs://your-bucket-name/your-object-name)';

// Create the Natural Language client
$languageServiceClient = new LanguageServiceClient();
try {
    // Create a new Document, pass GCS URI and set type to PLAIN_TEXT
    $document = (new Document())
        ->setGcsContentUri($uri)
        ->setType(Type::PLAIN_TEXT);

    // Call the analyzeEntitySentiment function
    $response = $languageServiceClient->analyzeEntitySentiment($document);
    $entities = $response->getEntities();
    // Print out information about each entity
    foreach ($entities as $entity) {
        printf('Entity Name: %s' . PHP_EOL, $entity->getName());
        printf('Entity Type: %s' . PHP_EOL, EntityType::name($entity->getType()));
        printf('Entity Salience: %s' . PHP_EOL, $entity->getSalience());
        $sentiment = $entity->getSentiment();
        if ($sentiment) {
            printf('Entity Magnitude: %s' . PHP_EOL, $sentiment->getMagnitude());
            printf('Entity Score: %s' . PHP_EOL, $sentiment->getScore());
        }
        print(PHP_EOL);
    }
} finally {
    $languageServiceClient->close();
}

Var denne siden nyttig? Si fra hva du synes:

Send tilbakemelding om ...

Cloud Natural Language API
Trenger du hjelp? Gå til brukerstøttesiden vår.