Surveys are a useful way to measure how happy your clients, employees, customers, or other stakeholders are. They can help you find out the pros and cons of your products, services, or processes, and give you useful feedback for improvement. However, surveys are not just about numbers and ratings. The most useful data from surveys are verbatims, or the open-ended responses that customers write in their own words. Verbatims can offer insights that you can’t get from ratings, such as the reasons why customers are satisfied or dissatisfied. Verbatims can also show the feelings and sentiments of customers, which can affect customer loyalty and retention. This post will show how to extract customer sentiment and the drivers of the feedback using Microsoft 365 Copilot.

A brief example:

Here are examples of an analysis report or table output from your survey data.

Introduction

Survey feedback is a valuable source of information for any business that wants to improve its products, services, and customer satisfaction. However, analyzing survey feedback can be a daunting and time-consuming task, especially when you have to deal with large volumes of text data.

How can you quickly and easily extract insights from your survey feedback without spending hours reading and coding every response? How can you identify the main themes, sentiments, and opinions of your customers and use them to make data-driven decisions?

The answer is Microsoft 365 Copilot, a new AI-powered tool that helps you analyze and categorize your survey feedback in minutes. In this blog post, we will show you how to use Microsoft 365 Copilot to do sentiment analysis and categorization of survey feedback and how it can benefit your business.

What is Microsoft 365 Copilot?

Microsoft 365 Copilot is an AI-powered productivity tool designed to enhance your work experience within the Microsoft 365 suite of applications.

Using Microsoft 365 Copilot for Sentiment Analysis and Categorization of Survey Feedback

Using Microsoft 365 Copilot for sentiment analysis and categorization of survey feedback is easy and intuitive. Typically survey data a spreadsheet for analysis. At the time of this writing, sentiment analysis is not supported by Copilot in Excel. However, we can use Copilot in Word’s ability to do sentiment analysis and theme categorization. Here are the steps you need to follow:

Note: There are capacity limits with the amount of data that can be analyzed. For the best results, it’s best to keep the input to a maximum size of about 1600 words.

Prepare your survey data for analysis.

You can use the included file ‘Hotel Stay Sample Feedback Data.xlsx’ with the steps below.

1. In Excel, hide columns that are not needed for the feedback analysis. By hiding the data not needed, you will be able to analyze more feedback records due to capacity limits. (See note above.)
2. Create a new empty Word document.
3. Select the data to analyze to the clipboard.
4. Paste the data table into the new Word document.
5. Save the Word document to your OneDrive. For example: ‘Hotel Stay Feedback.docx’

It should look like this:

Prompt: Use Copilot to create a Sentiment and Theme report

In this step, you will reference the Word document created in the last step. ‘Hotel Stay Feedback.docx’

1. Create a new Word document.
2. In the Copilot UI, enter the following prompt:

1
2
3
4
5
6

Draft a sentiment and theme report using this data
Hotel Stay Feedback.docx. The sentiment should be 
expressed as positive, negative or neutral. Each 
feedback should be associated with the theme 
with the highest corelation to the feedback.  
Include Summary, Analysis and Methodology sections. 

🗒️ Note that you need to explicitly link to the data file. That is, the name of the file itself won’t import the data. You need to use the ‘Reference your content’ button or the ‘/’ key to find and select your data file. The file will appear underlined when linked. See below.

🗒️ About this prompt: Note the we’re specifying how we want the sentiment classified: positive, negative or neutral. We can use whatever classification we deem appropriate here, for example we can replace it with a ratings scale: The sentiment should be expressed on a scale of 1 to 5 with 5 being most positive and 1 being the most negative. Additionally, for flexibility, prompt does not specify the themes, but asks Copilot to determine them with the following instructions: Each feedback should be associated with the theme with the highest corelation to the feedback.

🗒️ The output generated by Copilot (and all generative AI tools) is non-deterministic. This is a big difference in how we have traditionally worked with software applications. Providing more detail and context will help Copilot provide the expected results. Additionally, you can try the prompt again by using the ‘Regenerate’ button in Word.

Click this link to view what the output typically looks like.

Prompt: Use Copilot to create a table of the Sentiment and Theme data

The report is useful, but having a table of the sentiment and themes will also be useful. The following prompt will generate the table.

Again you will reference the Word document created in the last step. ‘Hotel Stay Feedback.docx’

1. Create a new Word document.
2. In the Copilot UI, enter the following prompt:

1
2
3
4
5
6
7

Draft a sentiment and theme table using this data 
Hotel Stay Feedback.docx Evaluate the drivers of the 
feedback into six main themes. The sentiment should be 
expressed as positive, negative or neutral. Each feedback 
should be associated with the theme with the highest 
corelation to the feedback. The table output should 
follow this pattern {number} {feedback} {sentiment} {theme}

Click this link to view what the output typically looks like.

Conclusion

Microsoft 365 Copilot is a powerful and easy-to-use tool that helps you analyze and categorize your survey feedback in minutes. It helps you understand the sentiment, tone, and emotion of your customers and how they relate to your business goals. It also helps you organize your feedback data into meaningful categories and labels that you can use to make data-driven decisions. If you want to learn more about Microsoft 365 Copilot and how it can help you improve your customer satisfaction and loyalty, visit the Copilot website or follow me on LinkedIn:.

Report: Sentiment and Theme Analysis of Hotel Stay Feedback Data

Hotel Stay Feedback Sentiment and Theme Report

Summary

This report presents the results of a sentiment and theme analysis of 58 hotel stay feedbacks collected from an online survey. The main objectives of the analysis are to identify the overall sentiment of the feedbacks, the most common themes associated with the feedbacks, and the relationship between sentiment and theme. The report also describes the methodology and the limitations of the analysis.

Analysis

The sentiment analysis was performed using a simple rule-based approach that assigns a positive, negative or neutral label to each feedback based on the presence of certain keywords. The keywords were manually selected based on a preliminary examination of the feedbacks. The following table shows the keywords and the corresponding sentiment labels.

The theme analysis was performed using a simple frequency-based approach that counts the occurrence of certain keywords related to different aspects of the hotel stay. The keywords were manually selected based on a preliminary examination of the feedbacks. The following table shows the keywords and the corresponding themes.

The results of the sentiment and theme analysis are summarized in the following table, which shows the number and percentage of feedbacks for each sentiment and theme combination.

The main findings of the analysis are:

• The overall sentiment of the feedbacks is evenly distributed, with 18 positive feedbacks, 18 negative feedbacks and 14 neutral feedbacks.
• The most common theme across all feedbacks is staff and service, followed by room quality, location and amenities. Breakfast is the least common theme.
• The most positive theme is location, with 16 positive feedbacks and 15 negative feedbacks. The most negative theme is staff and service, with 14 negative feedbacks and 16 positive feedbacks.
• The most neutral theme is breakfast, with 4 neutral feedbacks and 8 positive and negative feedbacks each.
• There is a strong correlation between sentiment and theme, with positive feedbacks tending to mention more positive aspects of the hotel stay and negative feedbacks tending to mention more negative aspects of the hotel stay.

Methodology

The methodology of the analysis consists of the following steps:

1. Collecting the hotel stay feedbacks from an online survey.
2. Preprocessing the feedbacks by removing punctuation, converting to lowercase, and tokenizing by words.
3. Assigning a sentiment label to each feedback based on the presence of certain keywords.
4. Assigning a theme label to each feedback based on the presence of certain keywords.
5. Counting the number and percentage of feedbacks for each sentiment and theme combination.
6. Summarizing the results and presenting the findings in a table and a list.

Limitations

The limitations of the analysis are:

• The sentiment and theme analysis is based on a simple rule-based approach that relies on manually selected keywords. This approach may not capture the nuances and subtleties of the feedbacks, such as sarcasm, irony, or context-dependent meanings.
• The sentiment and theme analysis is based on a small sample of 58 feedbacks, which may not be representative of the population of hotel stay feedbacks. The results may vary depending on the source and the size of the data.
• The sentiment and theme analysis does not account for the intensity or the polarity of the feedbacks, such as very positive, somewhat negative, or mixed. The results may not reflect the degree of satisfaction or dissatisfaction of the customers.

Report: Hotel Stay Feedback Analysis