Skip to content

Document-based Sentiment Analyzer

An opinion of something, about a product for example, can have a positive, negative, or neutral sense of value. Sentiment Analyzer is a module to find out the difference in each taste value from an opinion. The Document-based Sentiment Analyzer assesses the sentiment of a text as a whole (document level) with positive, negative, and neutral values.

The Document-based Sentiment Analyzer can be used by inputting articles or text and the software will give an output as sentiment value and its confidence score.

Illustration

Doc based Sentiment

Request Method

POST

Request URL

1
https://api.prosa.ai/v2/text/doc-sentiment

Request Header

Key Data Type Description Value
Content-Type string Media type of the body sent to the API. Only Support 'application/json' application/json
x-api-key string API Key Acquired from Prosa API Console [YOUR_API_KEY]

Request Body

The request body accepts the following parameter(s) in JSON format.

Parameter Data Type Description Auto Required
text string text to be processed True

Example

Sample Request (JSON)

1
2
3
{
  "text": "Aplikasi cukup membantu"
}

Sample Response (JSON)

1
2
3
4
5
6
7
8
9
{
    "setiment": [
        {
            "confidence": 0.999988267980654,
            "sentiment": "positive",
            "sentence": "Aplikasi cukup membantu"
        }
    ]
}

Sentiment Polarity Types

Polarity Description Example
Positive Text that contains positive reactions, positive opinions, or positive views on something. Melakukan ibadah di Masjid Alun-Alun Bandung sangat nyaman.
Negative Text that contains negative reactions, negative opinions, or negative views on something. Dia terlihat jelek dengan baju yang dikenakannya.
Neutral Text that does not contains subjective reactions, opinions, or views on something. Saya sedang belajar.

Free trial

Are you interested in our API? Click the button below and get your free trial now.

try now

Version History

Below is the version history for our Document-based Sentiment Analyzer API.

Version F1 Precision Recall Test Data
1.0 86.40% 85.80% 80.90% 500 sentences

Questions?

We do our best to make this documentation clear and user friendly, but if you have unanswered questions, please send email to support@prosa.ai.