Skip to main content

Sentiment Analysis (Beta)


In Beta

This feature is in Beta. If you have questions or comments, emailย support@symbl.ai.

Sentiment Analysis is the interpretation of the general thought, feeling, or sense of an object or a situation.

Symbl's Sentiment API works over Speech-to-Text sentences and Topics (or aspect).

Sentiment APIโ€‹

To see the Sentiment API in action, you need to process a conversation using Symbl. After you process a conversation, you'll receive a conversation Id which can be passed to the following Conversation APIs. All you need to do is pass the conversationId and query parameters sentiment=true.

info

Each continuous sentence spoken by a speaker in conversation is referred to as a Message. Hence ,we named our Speech to Text API as Messages API. Messages API returns you a list of messages in a conversation.

๐Ÿ‘‰Messages APIโ€‹

info

For topic level, the sentiment is calculated over the topic messages scope i.e. it factors in the sentiment of messages where the topic was talked about.

๐Ÿ‘‰Topics APIโ€‹

API Responseโ€‹

{
"messages": [
{
"id": "6412283618000896",
"text": "Best package for you is $69.99 per month.",
"from": {
"name": "Roger",
"email": "Roger@example.com"
},
"startTime": "2020-07-10T11:16:21.024Z",
"endTime": "2020-07-10T11:16:26.724Z",
"conversationId": "6749556955938816",
"phrases": [
{
"type": "action_phrase",
"text": "$69.99 per month"
}
],
"sentiment": {
"polarity": {
"score": 0.6
} ]
}

Objectโ€‹

FieldDescription
polarityShows the intensity of the sentiment. It ranges from -1.0 to 1.0, where -1.0 is the most negative sentiment and 1.0 is the most positive sentiment.
suggesteddisplay suggested sentiment type (negative, neutral and positive).

suggested objectโ€‹

info

We have chosen the below polarity ranges wrt sentiment type which covers a wide range of conversations. Polarity Sentiment may vary for your use case. We recommend that you define a threshold that works for you, and then adjust the threshold after testing and verifying the results.

PolaritySuggested Sentiment
-1.0 => x < -0.3negative
-0.3 => x <= 0.3neutral
0.3 > x <= 1.0positive

Tutorialsโ€‹

  • View tutorial on Sentiment Analysis on Messages here
  • View tutorial on Sentiment Analysis on Topics here