Unlocking Emotional Insights: A Developer's Guide to the curt-park Sentiment Analysis Actions

24 Apr 2025
Unlocking Emotional Insights: A Developer's Guide to the curt-park Sentiment Analysis Actions

In the world of natural language processing, understanding the emotional tone behind text is crucial for various applications, from customer feedback analysis to social media monitoring. The curt-park/sentiment-analysis API offers powerful Cognitive Actions that enable developers to perform sentiment analysis on text inputs effortlessly. With the pre-built actions provided, you can quickly integrate sentiment analysis capabilities into your applications, enhancing user experience and data-driven decision-making.

Prerequisites

Before diving into the sentiment analysis actions, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will allow you to authenticate and make requests.
  • Basic knowledge of JSON structure and HTTP requests.

To authenticate your requests, you will typically include your API key in the headers of your API calls. This is a common practice that helps secure your interactions with the platform.

Cognitive Actions Overview

Analyze Sentiment of Text

The Analyze Sentiment of Text action performs a detailed sentiment analysis on provided text inputs. It evaluates the emotional tone conveyed, categorizing it into varying sentiments, from positive to negative.

  • Category: Sentiment Analysis

Input

The input to this action consists of a JSON object that requires the following field:

  • text: A string containing the text you wish to analyze. This field is required.

Example Input:

{
  "text": "Hello World!"
}

Output

Upon execution, this action returns a JSON object containing:

  • label: A string indicating the sentiment category (e.g., "POSITIVE", "NEGATIVE").
  • score: A float representing the confidence score of the sentiment analysis, indicating how likely the text falls into the identified sentiment category.

Example Output:

{
  "label": "POSITIVE",
  "score": 0.9997431635856628
}

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might call the Analyze Sentiment of Text action using Python. This snippet demonstrates how to structure the input JSON payload and make a request to the Cognitive Actions API.

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"  # Hypothetical endpoint

action_id = "8bbf4ed4-c812-4d53-9c8d-5bb887737379"  # Action ID for Analyze Sentiment of Text

# Construct the input payload based on the action's requirements
payload = {
    "text": "Hello World!"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload}  # Hypothetical structure
    )
    response.raise_for_status()  # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, you will need to replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id is set to the ID of the sentiment analysis action, and the payload is structured according to the required input schema. The request is sent to the hypothetical endpoint, and the response is printed out, showing the sentiment analysis results.

Conclusion

The curt-park/sentiment-analysis actions provide a straightforward way for developers to integrate sentiment analysis into their applications. By leveraging the Analyze Sentiment of Text action, you can gain valuable insights into the emotional tone of user-generated content, enhancing your application's interactivity and responsiveness.

Consider exploring additional use cases for sentiment analysis, such as real-time feedback systems, content moderation, or enhancing customer support interactions. Happy coding!

← Back to All Articles