DAIN and DIANA - The Story Of Our Lives

As Diana is from Canada, she needs to be bilingual so it is important that when asked a question or told something that the language is detected.  If the text comes from Twitter then the tweet will contain the language, however if it comes from another source say Slack or text on a console, that language is not provided.  This is where language detection providers are so important. POC #1: Detection Via LanguageDetection Nuget Package Initially Dain and Diana used the LanguageDetection Nuget: Install-Package LanguageDetection This package is described as "Detect the language of a text using naive a Bayesian filter with generated language profiles from Wikipedia abstract xml, 99% over precision for 53 languages. Original author: Nakatani Shuyo." POC #2: Cognitive Services After some growth and chatting with Mark Stiles a second provider was created for Cognitive Services based on this article Quickstart: Identify language from text with the Translator Text REST API

It was a warm night in New Orleans in 2016, somewhere between the visit to the House of Blues the next morning. There were lots of conversations with many Sitecore MVPs regarding how people would interact with the Reputation Engine.  After quite a few drinks the decision was made and then came the birth of DAIN or as most people know him @SitecoreDain. There has been a lot of POC work done that has made it back into my core. Some of which will become articles on this blog. Now Dain was happy but was also a little lonely, he would bug SitecoreRobbie and Eric Ramseur and Corey Smith but he needed a companion. After some discussion with Dan Solovay and then not soon after Brent Pinkstaff, the decision was made to introduce Diana. The point of having the two personalities was to establish a way to A + B test the algorithms. Initially they both use the same algorithms but different initial data. This gave them the personality. Dain would act positive and Diana negative.  This worked