Use of Microsoft cognitive service in order to classify client email sentiment

As businesses continue to rely on emails for communication with clients, it becomes important to efficiently and accurately classify the sentiment of these emails. Sentiment analysis can help businesses identify positive, negative or neutral sentiment in emails, allowing them to prioritize and respond accordingly.

Microsoft Cognitive Services provides a variety of pre-built APIs that can be used for sentiment analysis. These APIs are easy to integrate and require minimal coding knowledge. In this article, we will explore how to use Microsoft Cognitive Services for sentiment analysis on client emails.

Step 1: Setting up the Microsoft Cognitive Services API

To get started, we need to set up an account with Microsoft Cognitive Services and obtain an API key. Follow the steps below:

1. Go to the Microsoft Cognitive Services website and sign up for an account.
2. Once you have signed up, you will be directed to the dashboard. From here, click on “Create a resource”.
3. Select “AI + Machine Learning” and choose “Text Analytics” from the available options.
4. Fill in the required information and select a pricing tier that meets your needs.
5. Once you have completed the setup, you will be provided with an API key that you can use to access the Text Analytics API.

Step 2: Setting up the Python Environment

Next, we need to set up our Python environment. We will be using the requests and json modules in Python for this task. If you do not have these modules installed, you can install them using pip. Run the following command:

pip install requests json

Step 3: Classifying Sentiment of Client Emails

Now that we have set up our Microsoft Cognitive Services API and Python environment, we can start classifying the sentiment of client emails. We will be using the Text Analytics API for this task.

First, we need to create a function that will take the email text as input and return the sentiment classification. Here’s an example:

import requests

import json

def get_email_sentiment(email_text, api_key):

    headers = {

        ‘Content-Type’: ‘application/json’,

        ‘Ocp-Apim-Subscription-Key’: api_key,

    }

    data = {

        “documents”: [

            {

                “id”: “1”,

                “text”: email_text

            }

        ]

    }

    response = requests.post(“https://<REGION>.api.cognitive.microsoft.com/text/analytics/v3.0-preview.1/sentiment”, headers=headers, json=data)

    sentiment = None

    if response.status_code == 200:

        response_data = json.loads(response.content.decode(‘utf-8’))

        sentiment = response_data[‘documents’][0][‘sentiment’]

    return sentiment

The function takes two parameters: the email text and the API key. It then creates the required headers and data for the Text Analytics API and sends a POST request to the API endpoint. The function then extracts the sentiment classification from the API response and returns it.

To use this function, simply call it with the email text and API key as parameters:

email_text = “Thank you for your prompt response. I am very satisfied with the service I received.”

api_key = “<YOUR_API_KEY>”

sentiment = get_email_sentiment(email_text, api_key)

print(sentiment)

This will output “positive”, indicating that the sentiment of the email is positive.

Conclusion

Sentiment analysis can help businesses efficiently and accurately classify the sentiment of client emails. Microsoft Cognitive Services provides an easy-to-use API for sentiment analysis that can be integrated into Python code. With just a few lines of code, businesses can extract valuable insights from client emails and respond accordingly.