Skip to content

Analyze Sentiment

Analyze text sentiment (reviews, comments, feedback, etc.) using AI-powered semantic understanding.

Sentiment analysis is multilingual, works across all supported languages.

Sentiments

Returns sentiment with one of the following values:

  • Positive - Text expresses predominantly positive sentiment
  • Negative - Text expresses predominantly negative sentiment
  • Neutral - Text expresses a balanced or ambiguous sentiment
Analyze Sentiment vs. Classify

This endpoint (Analyze Sentiment) performs sentiment analysis using AI-powered semantic understanding.

If you have 1,000 or more examples (per sentiment) specific to your use case, you can train a custom machine learning (ML) model, and then use the Classify endpoint to perform sentiment analysis. This will provide even better results as it uses AI-powered pattern recognition plus semantic understanding.

Endpoint

POST /v20241104/analyze-sentiment

API Request

  • Required Parameters

    API request must contain either a document_id array or a text array.

    document_id array of strings

    Array specifying one or more document IDs.

    Info

    • Example (single document ID): 

      "document_id": ["4nD1gZIB7caKVIeL2MgL"]

    • Example (multiple document IDs): 

      "document_id": ["4nD1gZIB7caKVIeL2MgL", "4wdRU5QBP4_EawzZupIF"]

    • For each document ID string:

      MinLength: 1   MaxLength: 128

    MinLength: 1   MaxLength: 10

    text array of strings

    Array specifying one or more text strings.

    Info

    • Example (single text value): 

      "text": [
    "I love my original Listerine. This came properly packaged so it didn鈥檛 leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean."
]

    • Example (multiple text values): 

      "text": [
    "I love my original Listerine. This came properly packaged so it didn鈥檛 leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
    "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado."
]

    • For each text string:

      MinLength: 1   MaxLength: 1000

    MinLength: 1   MaxLength: 10

  • POST /v20241104/analyze-sentiment

    curl -X POST "https://api.gainly.ai/v20241104/analyze-sentiment" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY_HERE" \  # (1)!
  -d '{
    "text": [
        "I love my original Listerine. This came properly packaged so it didn\'t leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
        "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado."
    ]
  }'
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    # Prompt for AI coding assistants/IDEs (e.g., ChatGPT, Claude, GitHub Copilot, Cursor, Windsurf)

Using the Gainly API:
1. Write code to call the analyze_sentiment operation (see OpenAPI spec: https://api.gainly.ai/v20241104/openapi.json)
2. Implement authentication using the header "X-API-Key" as described in the docs: https://docs.gainly.ai/latest/api-reference/authentication/
3. Implement rate limit handling as described in the docs: https://docs.gainly.ai/latest/api-reference/rate-limits/
4. Implement error handling
5. Handle the response according to the AnalyzeSentimentResults schema in the OpenAPI spec

    using System.Net.Http;
using System.Text.Json;
using System.Text;

var client = new HttpClient();

var url = "https://api.gainly.ai/v20241104/analyze-sentiment";

var payload = new {
    text = new[] { 
        "I love my original Listerine. This came properly packaged so it didn't leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
        "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado."
    }
};

var content = new StringContent(
    JsonSerializer.Serialize(payload),
    Encoding.UTF8,
    "application/json"
);

client.DefaultRequestHeaders.Add("X-API-Key", "YOUR_API_KEY_HERE"); // (1)!

var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "net/http"
)

func main() {
    url := "https://api.gainly.ai/v20241104/analyze-sentiment"

    payload := map[string]interface{}{
        "text": []string{
            "I love my original Listerine. This came properly packaged so it didn't leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
            "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado.",
        },
    }

    jsonData, _ := json.Marshal(payload)

    req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
    req.Header.Set("Content-Type", "application/json")
    req.Header.Set("X-API-Key", "YOUR_API_KEY_HERE") // (1)!

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()

    var result map[string]interface{}
    json.NewDecoder(resp.Body).Decode(&result)
    fmt.Println(result)
}
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;

var client = HttpClient.newHttpClient();

var url = "https://api.gainly.ai/v20241104/analyze-sentiment";

var payload = """
    {
        "text": [
            "I love my original Listerine. This came properly packaged so it didn't leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
            "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado."
        ]
    }
    """;

var request = HttpRequest.newBuilder()
    .uri(URI.create(url))
    .header("Content-Type", "application/json")
    .header("X-API-Key", "YOUR_API_KEY_HERE") // (1)!
    .POST(HttpRequest.BodyPublishers.ofString(payload))
    .build();

var response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    const axios = require('axios');  // or: import axios from 'axios';

const url = 'https://api.gainly.ai/v20241104/analyze-sentiment';

const payload = {
    text: [
        'I love my original Listerine. This came properly packaged so it didn\'t leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.',
        'Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado.'
    ]
};

const headers = {
    'Content-Type': 'application/json',
    'X-API-Key': 'YOUR_API_KEY_HERE' // (1)!
};

axios.post(url, payload, { headers })
    .then(response => console.log(response.data))
    .catch(error => console.error('Error:', error.message));
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    <?php

$client = new \GuzzleHttp\Client();

$url = 'https://api.gainly.ai/v20241104/analyze-sentiment';

$payload = [
    'text' => [
        'I love my original Listerine. This came properly packaged so it didn\'t leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.',
        'Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado.'
    ]
];

$response = $client->request('POST', $url, [
    'json' => $payload,
    'headers' => [
        'Content-Type' => 'application/json',
        'X-API-Key' => 'YOUR_API_KEY_HERE' # (1)!
    ],
]);

echo $response->getBody();
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    import requests

url = "https://api.gainly.ai/v20241104/analyze-sentiment"

payload = {
    "text": [
        "I love my original Listerine. This came properly packaged so it didn't leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
        "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado."
    ]
}

headers = {
    "Content-Type": "application/json",
    "X-API-Key": "YOUR_API_KEY_HERE" # (1)!
}

response = requests.post(url, json=payload, headers=headers)
data = response.json()
print(data)
    1. Replace YOUR_API_KEY_HERE with the value of your API key.
    require 'json'
require 'uri'
require 'net/http'
require 'openssl'

url = URI('https://api.gainly.ai/v20241104/analyze-sentiment')

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request['Content-Type'] = 'application/json'
request['X-API-Key'] = 'YOUR_API_KEY_HERE' # (1)!
request.body = {
    text: [
        'I love my original Listerine. This came properly packaged so it didn\'t leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.',
        'Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado.'
    ]
}.to_json

response = http.request(request)
puts response.read_body
    1. Replace YOUR_API_KEY_HERE with the value of your API key.

API Response

{
    "object": "analyze_sentiment_result",
    "url": "/v20241104/analyze-sentiment",
    "data": [
        {
            "sentiment": "positive",
            "confidence_level": "high",
            "text": "I love my original Listerine. This came properly packaged so it didn鈥檛 leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
            "document_id": null
        },
        {
            "sentiment": "negative",
            "confidence_level": "very_high",
            "text": "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado.",
            "document_id": null
        }
    ],
    "text": [
        "I love my original Listerine. This came properly packaged so it didn鈥檛 leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
        "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado."
    ],
    "document_id": null,
    "token_usage": {
        "semantic_tokens": 179,
        "llm_tokens": {
            "llm_output_tokens": 0,
            "llm_input_tokens": 0,
            "model": null
        }
    },
    "livemode": true
}

Sentiment

sentiment indicates Gainly's assessment of the emotional tone of the text.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
"data": [
    {
        "sentiment": "positive",
        "confidence_level": "high",
        "text": "I love my original Listerine. This came properly packaged so it didn鈥檛 leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
        "document_id": null
    },
    {
        "sentiment": "negative",
        "confidence_level": "very_high",
        "text": "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado.",
        "document_id": null
    }
],

It will have one of the following values:

  • positive
  • negative
  • neutral

Confidence Level

confidence_level represents Gainly's assessment of the degree of confidence in the sentiment analysis result.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
"data": [
    {
        "sentiment": "positive",
        "confidence_level": "high",
        "text": "I love my original Listerine. This came properly packaged so it didn鈥檛 leak. What more can I say. Kills germs by the millions. Great for use with my waterpick and I feel so clean.",
        "document_id": null
    },
    {
        "sentiment": "negative",
        "confidence_level": "very_high",
        "text": "Muy mala calidad, no lo recomiendo. Compr茅 estos zapatos esperando algo de buena calidad, pero me llev茅 una gran decepci贸n. Despu茅s de solo una semana de uso, la suela comenz贸 a despegarse y el material se ve desgastado. Adem谩s, no son nada c贸modos, el ajuste es extra帽o y causan molestias al caminar. No vale la pena el dinero, hay opciones mucho mejores por el mismo precio. No los volver铆a a comprar",
        "document_id": null
    }
],

It will have one of the following values:

  • very_high
  • high
  • medium
  • low