batch-detect-sentiments

Description

The API extracts aspect-based and sentence level sentiment in text records.

For aspect-based sentiment analysis, a set of aspects and their respective sentiment is returned for each record. Similarly, for sentence-level sentiment analysis, the sentiment is returned at the sentence level.

For sentiment analysis, confidence scores are provided for each of the classes (positive, negative, neutral and mixed).

Learn more about sentiment analysis here.

Limitations: - A batch may have up to 100 records. - A record may be up to 5000 characters long. - The total of characters to process in a request can be up to 20,000 characters.

Usage

oci ai language batch-detect-sentiments [OPTIONS]

Required Parameters

--documents [complex type]

List of Documents for detect sentiments. This is a complex type whose value must be valid JSON. The value can be provided as a string on the command line or passed in as a file using the file://path/to/file syntax.

The --generate-param-json-input option can be used to generate an example of the JSON which must be provided. We recommend storing this example in a file, modifying it as needed and then passing it back in via the file:// syntax.

Optional Parameters

--compartment-id, -c [text]

The OCID of the compartment that calls the API, inference will be served from pre trained model

--endpoint-id [text]

The endpoint which have to be used for inferencing. If endpointId and compartmentId is provided, then inference will be served from custom model which is mapped to this Endpoint.

--from-json [text]

Provide input to this command as a JSON document from a file using the file://path-to/file syntax.

The --generate-full-command-json-input option can be used to generate a sample json file to be used with this command option. The key names are pre-populated and match the command option names (converted to camelCase format, e.g. compartment-id –> compartmentId), while the values of the keys need to be populated by the user before using the sample file as an input to this command. For any command option that accepts multiple values, the value of the key can be a JSON array.

Options can still be provided on the command line. If an option exists in both the JSON document and the command line then the command line specified value will be used.

For examples on usage of this option, please see our “using CLI with advanced JSON options” link: https://docs.cloud.oracle.com/iaas/Content/API/SDKDocs/cliusing.htm#AdvancedJSONOptions

--level [text]

Set this parameter for sentence and aspect level sentiment analysis. Allowed values are: - ASPECT - SENTENCE

Accepted values are:

ASPECT, SENTENCE

Example using required parameter

Copy and paste the following example into a JSON file, replacing the example parameters with your own.

    oci ai language batch-detect-sentiments --generate-param-json-input documents > documents.json

Copy the following CLI commands into a file named example.sh. Run the command by typing “bash example.sh” and replacing the example parameters with your own.

Please note this sample will only work in the POSIX-compliant bash-like shell. You need to set up the OCI configuration and appropriate security policies before trying the examples.

    oci ai language batch-detect-sentiments --documents file://documents.json