1️⃣ AWS COMPREHEND - SENTIMENT ANALYSIS (FRONT-END) ===========================================

📋 ELEMENT DESCRIPTION
--------------------------------
AWS COMPREHEND - SENTIMENT ANALYSIS provides DETECT SENTIMENT action to determine the sentiment of input text. The front-end element is suitable for applications when reactivity is desired, such as but not limited to, mobile applications. It supports processing large text and automatically splits it into appropriate chunks to meet AWS requirements.

🔧 STEP-BY-STEP SETUP
--------------------------------
ℹ️ The steps from 0) to 1) can be automatically performed by using this deployment template:
https://console.aws.amazon.com/cloudformation/home?#/stacks/create/review?stackName=BubbleComprehendSyncOnly&templateURL=https://bubble-resources.s3.amazonaws.com/deployment-assets/CloudFormation-AWSComprehendSyncOnly.yaml

You will find the required parameters values used across the plugin in the "OUTPUT" tab of the created stack.

0) Sign-up for AWS COMPREHEND by following this link: https://console.aws.amazon.com/comprehend/home?p=ply&cp=bn&ad=c

1) Create your AWS COMPREHEND ACCESS KEY & ACCESS KEY SECRET and attach the AWS COMPREHEND READ-ACCESS policy: https://docs.aws.amazon.com/general/latest/gr/aws-sec-cred-types.html#access-keys-and-secret-access-keys

2) Register on plugins.wiseable.io. Create a new Credential which associates your BUBBLE APP URL, AWS COMPREHEND ACCESS KEY & ACCESS KEY SECRET.
The registration service will generate your PUBLIC ACCESS KEY. This key serves as a secure proxy for your real API key. It allows your application to communicate with the service without exposing your real API key. Since this PUBLIC ACCESS KEY is explicitly tied to your registered BUBBLE APP URL, it can only be used from that domain, ensuring that even if the key is publicly visible, it remains safe and cannot be misused by unauthorized sources.

3) Enter in the PLUGIN SETTINGS your PUBLIC ACCESS KEY (used for this element only), AWS SERVICE ENDPOINT REGION (if not provided, the default endpoint is "us-east-1").

4) Add the AWS COMPREHEND - SENTIMENT ANALYSIS (FRONT-END) element to the page on which the sentiment analysis feature must be integrated. Select the RESULT DATA TYPE as Returned type, must always be set to "RESULT (COMPREHEND - SENTIMENT ANALYSIS)".

5) Integrate the logic into your application using the following AWS COMPREHEND - SENTIMENT ANALYSIS (FRONT-END) element's states and actions:

FIELDS:
- RESULT DATA TYPE: Returned type, must always be set to "RESULT (COMPREHEND - SENTIMENT ANALYSIS)".

EVENTS:
- SUCCESS: Event triggered upon success
- ERROR: Event triggered upon error

EXPOSED STATES:
Use any element able to show/process the data of interest (such as a Group with a Text field) stored within the result of the following states of the AWS COMPREHEND - SENTIMENT ANALYSIS (FRONT-END) element:
- RESULTS: Populated upon SUCCESS event. Returns a score for each sentiment type, such as positive, neutral, mixed, negative, and the prevailing one.
- ERROR MESSAGE: Populated upon ERROR event.
- IS PROCESSING: Set to true when processing is in progress, false otherwise.

ELEMENT ACTIONS - TRIGGERED IN WORKFLOW:
- DETECT SENTIMENT (FRONT-END): Determine the sentiment of an input text. Populates RESULTS state upon completion.

  Input Fields:
     - TEXT TO ANALYZE: A UTF-8 text string. Each string should contain at least 20 characters and must contain fewer that 5,000 bytes of UTF-8 encoded characters.
     - LANGUAGE CODE: The language of the input text. You can specify any of the primary languages supported by AWS COMPREHEND. All documents must be in the same language. Possible values are listed here: https://docs.aws.amazon.com/comprehend/latest/dg/how-languages.html
     For automated language detection, please use our "AWS Comprehend - Language Detection" plugin.

2️⃣: DETECT SENTIMENT (BACK-END)
==================================

📋 ACTION DESCRIPTION
--------------------------------
DETECT SENTIMENT determines the sentiment of an input text. The back-end action is suitable for applications when volume or asynchronous processing is desired.

🔧 STEP-BY-STEP SETUP
--------------------------------
ℹ️ If not already done, perform steps 0, 1, and 3 of the first element setup. The back-end action does not require the PUBLIC ACCESS KEY.

1) Set up the "DETECT SENTIMENT (BACK-END)" action in the workflow.

  Input Fields:
     - TEXT TO ANALYZE: A UTF-8 text string. Each string should contain at least 20 characters and must contain fewer that 5,000 bytes of UTF-8 encoded characters.
     - LANGUAGE CODE: The language of the input text. You can specify any of the primary languages supported by AWS COMPREHEND. All documents must be in the same language. Possible values are listed here: https://docs.aws.amazon.com/comprehend/latest/dg/how-languages.html
     For automated language detection, please use our "AWS Comprehend - Language Detection" plugin.
 
  Output Fields:
     - RESULTS: Returns a score for each sentiment type, such as positive, neutral, mixed, negative, and the prevailing one.

🔍 IMPLEMENTATION EXAMPLE
======================
Feel free to browse the app editor in the Service URL for an implementation example.

ℹ️ ADDITIONAL INFORMATION
======================
> Detect Sentiment details: https://docs.aws.amazon.com/comprehend/latest/dg/how-sentiment.html
> AWS COMPREHEND service limits: https://docs.aws.amazon.com/comprehend/latest/dg/guidelines-and-limits.html#limits-all
> AWS services availability per region: https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/
> AWS Service endpoints list: https://docs.aws.amazon.com/general/latest/gr/rande.html

⚠️ TROUBLESHOOTING
================
Any plugin related error will be posted to the Logs tab, "Server logs" section of your App Editor.
Make sure that "Plugin server side logging" and "Plugin client side logging" are selected in "Show Advanced".

For front-end actions, you can also open your browser's developer console (F12 or Ctrl+Shift+I in most browsers) to view detailed error messages and logs.

Always check the ERROR MESSAGE state of the element and implement error handling using the ERROR event to provide a better user experience.

> Server Logs Details: https://manual.bubble.io/core-resources/bubbles-interface/logs-tab#server-logs

⚡ PERFORMANCE CONSIDERATIONS
===========================

GENERAL
-------------
For back-end actions, the maximum processing duration of this action is capped at 30 seconds as per Bubble.io design. This time limitation does not apply to front-end actions.

⏱️ BACK-END ACTION START DELAY
-----------------------------------------------
Each time a server-side action is called, Bubble initializes a small virtual machine to execute the action. If the same action is called shortly after, the caching mechanism kicks in, resulting in faster execution on subsequent calls.

A useful workaround is to fire a dummy execution at page load, which pre-warms the Bubble engine for the next few minutes, reducing the impact of cold starts for your users.

FRONT-END VS BACK-END PROCESSING
----------------------------------------------------
The front-end element is designed to support and process large text by automatically splitting it into chunks that adhere to AWS requirements. The back-end action also performs this optimization to ensure proper processing.

❓ QUESTIONS?
===========
Contact us at [email protected] for any additional feature you would require or support question.