SENTIMENT ANALYSIS USING AWS SNS AND AWS COMPREHEND (not at free of cost)

Описание: In this video, we explore how to perform Sentiment Analysis using AWS Comprehend and trigger notifications with AWS SNS. Learn how to analyze text sentiment (positive, negative, neutral, or mixed) and automate alerts based on the results. Perfect for AI-driven customer feedback analysis, social media monitoring, and more! 🚀

🔹 What You’ll Learn:
✅ Introduction to AWS Comprehend & SNS
✅ Setting up sentiment analysis in AWS
✅ Automating alerts with SNS
✅ Hands-on demo with real-world use cases

Also they charge me 0.65 dollar for sms notifications..

Don't forget to like, share, and subscribe for more cloud and AI tutorials! 🔥💡

ESSENTIALS:

"Sentiment Analyzer"


ROLES:
AmazonSNSFullAccess
AWSLambdaBasicExecutionRole
ComprehendFullAccess

FUNCTION NAME:sentiment-analysis

FUNCTION CODE:

import json
import boto3

Initialize AWS clients
comprehend = boto3.client("comprehend")
sns = boto3.client("sns")

Replace with your correct SNS Topic ARN (without the extra subscription ID)
SNS_TOPIC_ARN = "arn:aws:sns:us-east-1:050752635754:SentimentAlerts"

def lambda_handler(event, context):
try:
Parse input text
body = json.loads(event.get("body", "{}"))
text = body.get("text", "").strip()

if not text:
return {
"statusCode": 400,
"body": json.dumps({"error": "No text provided for sentiment analysis"})
}

Perform sentiment analysis
response = comprehend.detect_sentiment(Text=text, LanguageCode="en")
sentiment = response["Sentiment"]

Prepare SNS message
message = f"Sentiment Analysis Result: {sentiment}\n\nText: {text}"

Publish message to SNS
sns.publish(TopicArn=SNS_TOPIC_ARN, Message=message)

return {
"statusCode": 200,
"body": json.dumps({"sentiment": sentiment, "message": "Notification sent successfully!"})
}

except Exception as e:
return {
"statusCode": 500,
"body": json.dumps({"error": str(e)})
}

LAMBDA EVENT CODE:

{
"body": "{\"text\": \"I hate this service!\"}"
}

SNS NAME:SentimentAlerts


URL:https://iojdihzccj.execute-api.us-eas...

BODY:
{
"text": "i hate aws!!"
}