Text Emotion Analysis

The Emotion Analysis model will help you understand and interpret emotions in a conversation or text. It is designed to understand human conversation in the form of free text and is designed after the emotion wheel.

Emotion Types

Types of Emotions detected by enabling this model configuration in the Speech Analytics API:

Admiration Amusement Anger Annoyance Approval Caring Confusion Curiosity Desire Disappointment Disapproval Disgust Embarrassment Excitement Fear Gratitude Grief Joy Love Nervousness Optimism Pride Realization Relief Remorse Sadness Surprise Neutral

API Request

Returns the predicted emotion for a given sentence

POST https://api.marsview.ai/text/emotion/get_emotion

Query Parameters

Name	Type	Description
jwtToken*	String	Marsview api access token. You can generate it here: https://docs.marsview.ai/speech-analytics-api/authentication
sentence*	String	The sentence you want to detect emotion
userId*	String	Your Marsview user ID

200: OK Response with detected emotion labels

{
    "status": true,
    "error": {},
    "data": {
        "text": "I love building things that change things",
        "labels": [
            {
                "value": "LOVE",
                "confidence": 0.9979714751243591
            }
        ]
    },
    "userId": "[e-mail]"
}

400: Bad Request When a bad request is sent with missing key

{
    "status": false,
    "error": {
        "message": "Bad Request Missing key",
        "code": "RTSEMO002"
    },
    "data": {},
    "userId": "[e-mail]"
}

401: Unauthorized When the user requested with an invalid jwt token

{
    "status": false,
    "message": "Something went wrong while validating your JWT token."
}

Example Curl Request

Shown below is a code snippet to send a sample request to the emotion analysis

curl --location --request POST 'https://api.marsview.ai/text/emotion/get_emotion' \
--header 'Content-Type: application/json' \
--data-raw '{
    "jwtToken": "Insert JWT token Key",
    "sentence": "Insert your sentence for emotion detection here",
    "userId"  : "[e-mail]"
}'

Example Response

Shown below is a sample JSON response from the above request.

{
    "status": true,
    "error" : {},
    "data"  : {
        "text": "I love building things that change things",
        "labels": [
            {
                "value": "LOVE",
                "confidence": 0.9979714751243591
            }
        ]
    },
    "userId": "[e-mail]"
}

Response Object

Field	Description
text	The sentence / phrase for which the emotion is predicted
labels	The emotion labels identified by the models
confidence	Confidence of the predicted emotion
value	The predicted emotion