Fine tuning your sentiment models

• How do sentiment models work?
• Dashboard
  • Create a sentiment model
  • Add an example sentiment model
• Sentiment Models
  • Multiwords
  • Settings
  • Build/Test a model
  • Import/Export a model
  • Using a model
• Entries
  • Subentries
  • Advanced settings
• Fine tuning
  • Checking your results
  • Optimization tips

After the initial definition of a sentiment model, there will generally be an optimization phase, in which the correct detection and behavior of the entries added will be tested in the API they are going to be used in.

The first thing you need to know is how to identify which entries are being taken into account in the sentiment analysis. For that, we provide three tools:

• The polarity_term_list in the standard output of the Sentiment Analysis API.
• The tag_stack that appears with the verbose parameter enabled in both the Sentiment Analysis and Lemmatization, PoS and Parsing APIs.
• The image output (of=img) in the Lemmatization, PoS and Parsing API.

In the following section we will explain in detail how to use each one of these.

Once you know how to check the sentiment analysis you are getting from the APIs, we will give you some tips on common issues and how to approach them.