gcloud beta ml language analyze-entity-sentiment - use Google Cloud Natural Language API to identify entity-level sentiment
gcloud beta ml language analyze-entity-sentiment (--content=CONTENT | --content-file=CONTENT_FILE) [--content-type=CONTENT_TYPE; default="plain-text"] [--encoding-type=ENCODING_TYPE; default="utf8"] [--language=LANGUAGE] [GCLOUD_WIDE_FLAG ...]
(BETA) Entity level sentiment combines both entity analysis and sentiment analysis and attempts to determine the sentiment (positive or negative) expressed about entities within the text.
Currently only English is supported for this feature.
To analyze entity sentiment in raw content 'puppies':
$ gcloud beta ml language analyze-entity-sentiment \ --content='puppies'
To analyze entity sentiment in file 'myfile.txt':
$ gcloud beta ml language analyze-entity-sentiment \ --content-file='myfile.txt'
To analyze entity sentiment in a remote file 'gs://bucket_name/mycontent.html' for Japanese language using UTF-8 encoding:
$ gcloud beta ml language analyze-entity-sentiment \ --content-file='gs://bucket_name/mycontent.html' \ --content-type=HTML --encoding-type=utf8 --language=ja-JP
- Exactly one of these must be specified:
- --content=CONTENT
Specify input text on the command line. Useful for experiments, or for extremely short text.
- --content-file=CONTENT_FILE
Specify a local file or Google Cloud Storage (format gs://bucket/object) file path containing the text to be analyzed. More useful for longer text or data output from another system.
- --content-type=CONTENT_TYPE; default="plain-text"
Specify the format of the input text. CONTENT_TYPE must be one of: html, plain-text.
- --encoding-type=ENCODING_TYPE; default="utf8"
The encoding type used by the API to calculate offsets. If set to none, encoding-dependent offsets will be set at -1. This is an optional flag only used for the entity mentions in results, and does not affect how the input is read or analyzed. ENCODING_TYPE must be one of: none, utf16, utf32, utf8.
- --language=LANGUAGE
Specify the language of the input text. If omitted, the server will attempt to auto-detect. Both ISO (such as en or es) and BCP-47 (such as en-US or ja-JP) language codes are accepted.
These flags are available to all commands: --access-token-file, --account, --billing-project, --configuration, --flags-file, --flatten, --format, --help, --impersonate-service-account, --log-http, --project, --quiet, --trace-token, --user-output-enabled, --verbosity.
Run $ gcloud help for details.
This command uses the language/v1beta2 API. The full documentation for this API can be found at: https://cloud.google.com/natural-language/
This command is currently in beta and might change without notice. These variants are also available:
$ gcloud ml language analyze-entity-sentiment
$ gcloud alpha ml language analyze-entity-sentiment