Determining the sentiment and tone of a customer can help you to find the best conversations to review.
With the Klaus Sentiment filter, you can filter out the conversation in which the customer sentiment is judged to have been either positive or negative.
How does it work?
You can simply create a new filter and add the rule 'Sentiment is Positive/Negative'.
This will show you all of the conversations in which Klaus has found either Positive or Negative sentiment.
The messages in the conversation which have positive or negative sentiment will be marked either with a green smiley face or a red frown face.
You can also use the timeline to identify where these messages lie in the thread and quickly jump to them.
How do we calculate this?
We use state-of-the-art Natural Language Processing models to assign sentiment to customer messages.
Our data shows that sentiment strongly correlates with CSAT values i.e. negative conversations tend to get lower CSAT values. This makes the sentiment filter an efficient tool for learning which kind of conversations results in unsatisfied customers.
Sometimes, negative sentiment does not necessarily mean that the customer is frustrated, but it can mean that the message describes a complex problem that is conveyed with some negative vocabulary of a standard language.
Of course, no machine learning model is perfect and the quality of the output is dependent on the type of text. If the message contains production code, long sequences of numbers or letters, and other non-word text, this all makes it harder for the machine to properly process the input which can lead to an inaccurate judgment.