14.3 aztext demo

The pre-built demonstration highlights the capabilities of the package.

ml demo aztext

Here is a sample of the interaction.

Azure Text Analytics

Welcome to a demo of the pre-built models for Text Analytics provided
through Azure's Cognitive Services. This service extracts information
from text that we supply to it, providing information such as the
language, key phrases, sentiment (0-1 as negative to positive), and

Press Enter to continue: 

Language Information

We will first demonstrate the automated identification of language.
Below are a few "documents" in different languages which are passed on
to the  cloud for processing using the following language API URL:

Press Enter to continue: 

1 Text as a sample document written in English.
  This is English (en) with score of 1.0.

2 Este es un document escrito en EspaƱol.
  This is Spanish (es) with score of 1.0.


Sentiment Analysis

Now we look at an analysis of the sentiment of the document/text. This
is done so by passing the text of the text on to the sentiment API URL
shown below for processing in the cloud. The results are returned as a
number between 0 and 1 with 0 being the most negative and 1 being the
most positive.

Press Enter to continue: 

1 I had a wonderful experience! Rooms were wonderful and staff helpful.
  This has a sentiment rating of 0.97.

2 I had a terrible time at the hotel. The staff was rude and food awful.
  This has a sentiment rating of 0.00.



Our final demonstration identifies the entities refered to in the
text. As a bonus the API generates a link to Wikipedia for more
information! As  above, the text is passed on to the cloud through the
API at the URL below.


Your donation will support ongoing development and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2021 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0.