分析实体情感

实体情感分析 将实体分析和情感分析结合起来,并力图确定文本内实体表达的情感(正面还是负面)。 实体情感用数字分数和量值来表示,并且由实体的每次提及确定。 然后将这些分数汇总为实体的总体情感分数和量级。 如需了解如何解读分析中包含的 scoremagnitude 情感值,请参阅解读情感分析值

以下示例展示了如何查询 analyzeEntitySentiment 方法。 您必须针对每个文档分别提交请求。

分析实体情感

以下示例展示如何分析以字符串形式提供的实体的情感:

协议

如需分析文档中的实体情感,请按照下面示例中所示,向 documents:analyzeEntitySentiment REST 方法发出 POST 请求,并提供相应的请求正文。

该示例使用 gcloud auth application-default print-access-token 命令获取通过 Google Cloud Platform Cloud SDK 为项目设置的服务帐号的访问令牌。如需了解有关安装 Cloud SDK 以及使用服务帐号设置项目的说明,请参阅快速入门

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

如需查看完整的详细信息,请参阅 analyze-entity-sentiment 命令。

如需执行实体情感分析,请使用 gcloud 命令行工具并使用 --content 标志来标识要分析的内容:

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."

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

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_ = language_v1.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 = language_v1.EncodingType.UTF8

    response = client.analyze_entity_sentiment(request = {'document': 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(language_v1.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(language_v1.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))

其他语言

C#: 请按照客户端库页面上的 C# 设置说明操作,然后访问 .NET 版 Natural Language 参考文档。

PHP: 请按照客户端库页面上的 PHP 设置说明操作,然后访问 PHP 版 Natural Language 参考文档。

Ruby: 请按照客户端库页面上的 Ruby 设置说明操作,然后访问 Ruby 版 Natural Language 参考文档。

分析 Cloud Storage 中的实体情感

以下示例介绍如何分析 Cloud Storage 上文本文件中存储的实体情感:

协议

如需分析 Cloud Storage 中存储的文档的实体情感,请向 documents:analyzeEntitySentiment REST 方法发出 POST 请求,并提供带有文档路径的相应请求正文,如以下示例所示。

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

如需查看完整的详细信息,请参阅 analyze-entity-sentiment 命令。

如需执行实体情感分析,请使用 gcloud 命令行工具并使用 --content 标志来标识要分析的内容:

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

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

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_ = language_v1.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 = language_v1.EncodingType.UTF8

    response = client.analyze_entity_sentiment(request = {'document': 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(language_v1.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(language_v1.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))

其他语言

C#: 请按照客户端库页面上的 C# 设置说明操作,然后访问 .NET 版 Natural Language 参考文档。

PHP: 请按照客户端库页面上的 PHP 设置说明操作,然后访问 PHP 版 Natural Language 参考文档。

Ruby: 请按照客户端库页面上的 Ruby 设置说明操作,然后访问 Ruby 版 Natural Language 参考文档。