Sentiment analysis with Excel

I love the opportunity that is here right now, the opportunity to do cool stuff with data. At this moment there is so much available, and if it isn’t there you can simply build it. For me the so called “applied AI” examples are great and really show the power of all that is already out there and sparks the imagination for what’s possible.

This example of a Sentiment Analysis in Excel based on a Microsoft Cognitive Service is a great way to show how easy it can be to use these services. You don’t need to build everything yourself, if you have the data you can have results in minutes.

You can download the example here.

What is Sentiment Analysis

Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processingtext analysiscomputational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine.

Get the Sentiment in 3 steps

Step 1: Get your data that you want to analyse and paste it in an Excel sheet in column A. You can use any header name you like. I used “Restaurant Review”

Step 2: Configure the Azure Machine Learning Text Sentiment Analysis add-in.
Go to Insert -> Get Add-ins. Choose Data-Analytics (or search for Azure Machine Learning)

Add Azure Machine Learning to Excel

Choose the Text Sentiment Add-in

Configure it. Tell the Add-in where the reviews are, in this case from A2 till A12 and define where the ouput should start. B2. Make sure to uncheck “my data has headers

Step 3: Click Predict and see the magic happen. In Column B & C you will find the scores. In the example that you can download (here) you also see that is it bi-langual. I added a French and Dutch review.


It’s so easy

{start the world is great talk}
Use it in an interface, during your ETL process or after someone posts a review on your site. Use it to categorize incoming emails and learn which score needs your attention first. Use it to see improvements and to discover new insights and great ideas to optimize your processess. Use these kind of models to finally make the impact and show that data really is the new gold.
{end of the world is great talk}

Geef een reactie

Gelieve met een van deze methodes in te loggen om je reactie te plaatsen: logo

Je reageert onder je account. Log uit /  Bijwerken )

Google photo

Je reageert onder je Google account. Log uit /  Bijwerken )


Je reageert onder je Twitter account. Log uit /  Bijwerken )

Facebook foto

Je reageert onder je Facebook account. Log uit /  Bijwerken )

Verbinden met %s