View source for Using email bots for Natural Language Processing and Machine Learning

== Start Training ==

Once you have an idea of the initial scope of your email bot you can create start training your topics and entities.  One easy way to start this training is to use the '''Training Data''' tab of the Email channel. (Image 2).  This tab will show the text of emails that were already triaged if you previously enabled the '''Record training data''' check box for your Email channel.  You can also easily add new entries manually (animation 1).  It is often easiest to just think about different ways your users will initiate an action and quickly add them for each topic. For more information about training the email bot, see [https://community.pega.com/knowledgebase/articles/conversational-channels/85/training-model-email-channel Training the model for the Email channel]. 
[[File:Training Data.png|alt=Training NLP model data using the Training Data screen in App Studio.|thumb|Training NLP model data using the Training Data screen in App Studio.]] 

Now that you have data on the '''Training Data''' tab you can select an item, choose the appropriate topic, highlight and then right click to add entities, then mark the record as reviewed.  Start with 20 entries for each topic and entity as a baseline.  At any point you can build the model and start testing it directly from the training data screen.  This allows you to quickly iterate through the process of building an intelligent bot and evaluating its accuracy. 

There are other ways to build and enhance your model by using Pega Prediction Studio™ but those are more complex and will be covered in another article.

'''Note:''' To learn about text analysis and using NLP to detect the correct information from user emails, see [https://community.pega.com/knowledgebase/articles/conversational-channels/85/understanding-text-analysis Understanding text analysis].