Phil Ferriere
June 2016

MSCSShiny is a test/demo application for R packages like {mscstexta4r} and {mscsweblm4r} that interface with the Microsoft Cognitive Services REST APIs.

Demo: Try it live on shinyapps.io!

Microsoft Cognitive Services -- formerly known as Project Oxford -- are a set of large, diverse, truly awesome APIs, SDKs and services that developers can use to add AI features to their apps. Those features include emotion and video detection; facial, speech and vision recognition; as well as speech and NLP.

Our interest, at this stage, is limited to the exploration and evaluation of the NLP features of MSCS:

As should be clear from the above, this subset itself isn't exactly small...

The {mscstexta4r} package is a wrapper around the MSCS Text Analytics REST API. This API offers a suite of text analytics web services - built with Azure Machine Learning - that can be used to analyze unstructured text. The API supports the following operations:

• Sentiment analysis - Is a sentence or document generally positive or negative?
• Topic detection - What's being discussed across a list of documents/reviews/articles?
• Language detection - What language is a document written in?
• Key talking points extraction - What's being discussed in a single document?

For more information about the {mscstexta4r} package (on CRAN, or on GitHub), please check out the Text Analytics API tab at the top of this page.

The {mscsweblm4r} R package exposes bindings for the MSCS Web Language Model REST API. Per Microsoft's website, this API uses smoothed backoff N-gram language models (supporting Markov order up to 5) that were trained on four web-scale American English corpora collected by Bing (web page body, title, anchor and query). The following operations are supported:

• Calculate the joint probability that a sequence of words will appear together.
• Compute the conditional probability that a specific word will follow an existing sequence of words.
• Get the list of words (completions) most likely to follow a given sequence of words.
• Insert spaces into a string of words adjoined together without any spaces (hashtags, URLs, etc.).
• Retrieve the list of supported language models.

For additional information on the {mscsweblm4r} package (on CRAN, or on GitHub), please click the Web Language Model API tab at the top of this page.

All Microsoft Cognitive Services components are Copyright (c) Microsoft.

Customized progress bar style, courtesy of @jackolney.

Please report any MSCSShiny issues or bugs here.

License: MIT + file

This project is released with a Contributor Code of Conduct. By participating in this project, you agree to abide by its terms.