I am using Watson Natural Language Understanding for natural language processing in my master thesis. When building a custom model via Watson Knowledge Studio I have two choices:

• rule based annotator

• machine learning annotator

In the documentation I only found this:

"Use IBM Watson™ Knowledge Studio to create a machine-learning model that understands the linguistic nuances, meaning, and relationships specific to your industry or to create a rule-based model that finds entities in documents based on rules that you define." (https://console.bluemix.net/docs/services/knowledge-studio/index.html#wks_overview_full)

Somewhere else I also read that machine learning keeps improving / learning the more you use it. What other differences are there?

I am analyzing customer reviews with focus on sentiment. I need to justify my choice in my thesis so I would appreciate more information to make an informed decision. What model should I choose and why?