SentimentFilter - Amazon Transcribe
ContentsSee Also

SentimentFilter

Flag the presence or absence of specific sentiments detected in your Call Analytics transcription output.

Rules using SentimentFilter are designed to match:

  • The presence or absence of a positive sentiment felt by the customer, agent, or both at specified points in the call

  • The presence or absence of a negative sentiment felt by the customer, agent, or both at specified points in the call

  • The presence or absence of a neutral sentiment felt by the customer, agent, or both at specified points in the call

  • The presence or absence of a mixed sentiment felt by the customer, the agent, or both at specified points in the call

See Rule criteria for post-call categories for usage examples.

Contents

Sentiments

Specify the sentiments that you want to flag.

Type: Array of strings

Array Members: Fixed number of 1 item.

Valid Values: POSITIVE | NEGATIVE | NEUTRAL | MIXED

Required: Yes

AbsoluteTimeRange

Makes it possible to specify a time range (in milliseconds) in your audio, during which you want to search for the specified sentiments. See AbsoluteTimeRange for more detail.

Type: AbsoluteTimeRange object

Required: No

Negate

Set to TRUE to flag the sentiments that you didn't include in your request. Set to FALSE to flag the sentiments that you specified in your request.

Type: Boolean

Required: No

ParticipantRole

Specify the participant that you want to flag. Omitting this parameter is equivalent to specifying both participants.

Type: String

Valid Values: AGENT | CUSTOMER

Required: No

RelativeTimeRange

Makes it possible to specify a time range (in percentage) in your media file, during which you want to search for the specified sentiments. See RelativeTimeRange for more detail.

Type: RelativeTimeRange object

Required: No

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: