Sentiment Analysis

sentiment boolean   Default: false

Deepgram’s Sentiment Analysis feature recognizes the sentiment of the entire transcript and detects shifts in sentiment throughout the transcript.

A sentiment of positive, negative, or neutral along with a sentiment_score is identified for each segment of the transcript, and an average of the entire transcript’s sentiment is also provided along with the average sentiment_score.

This sentiment feature produces sentiment analysis at every level of transcription requested, so you’ll get sentiment values for every word, sentence, utterance, and paragraph, in addition to the top-level sentiment for the entire transcription.

Enable Feature

To enable Sentiment, use the following parameter in the query string when you call Deepgram’s /listen endpoint:

sentiment=true

To transcribe audio from a file on your computer, run the following curl command in a terminal or your favorite API client.

$
curl \
>
  --request POST \
>
  --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
>
  --header 'Content-Type: audio/wav' \
>
  --data-binary @youraudio.wav \
>
  --url 'https://api.deepgram.com/v1/listen?sentiment=true'

Query Parameters

Analyze Response

When the file is finished processing, you’ll receive a JSON response that has the following basic structure:

1
"metadata": {...},
2
  "results": {
3
    "channels": [
4
      {
5
        "alternatives": [...]
6
      }
7
    ],
8
    "sentiments": {
9
      "segments": [
10
        {
11
          "text": "Hi there. I love my current phone, but want a new one.",
12
          "start_word": 0,
13
          "end_word": 11,
14
          "sentiment": "positive",
15
          "sentiment_score": 0.4443286657333374
16
        },
17
        {
18
          "text": "Can I upgrade my phone?",
19
          "start_word": 12,
20
          "end_word": 16,
21
          "sentiment": "neutral",
22
          "sentiment_score": 0.1317894160747528
23
        }
24
      ],
25
      "average": {
26
        "sentiment": "positive",
27
        "sentiment_score": 0.35909067500721326
28
      }
29
    }
30
  }
31
}

The sentiment values added to objects are:

• sentiment: The sentiment of the associated text (‘positive’ | ‘negative’ | ‘neutral’).
• sentiment_score: A floating point value between -1 and 1 representing the sentiment of the associated span of text. -1 being the most negative sentiment, and 1 being the most positive sentiment.

Response Properties

API Warning Response

Warning

If you request Sentiment Analysis with an unsupported language by specifying a language code such as sentiment=true&language=es or sentiment=true&detect_language=true where the detected language is unsupported, you will get the warning message below.

1
"warnings": [
2
  {
3
    "parameter": "sentiment",
4
    "type": "unsupported_language",
5
    "message": "Sentiment is only supported for English."
6
  }
7
]

Example Warning

Here is an example of the JSON structure of a request with warning object.

1
{
2
 "metadata": {
3
...
4
       },
5
     "warnings": [
6
       {
7
         "parameter": "sentiment",
8
         "type": "unsupported_language",
9
         "message": "Sentiment is only supported for English."
10
       }
11
     ]
12
   },
13
 "results": {
14
       "channels": [
15
            {
16
                "alternatives": [...]
17
            }
18
        ], 
19
20
    }
21
}