We here at Klaus have a secret lab where we work on solutions to issues that matter most to customer support teams. So, while our One Taco For One Ticket™ feature is still being checked over by our legal department, we’re proud to announce the next best thing: The Sentiment Filter!
The Sentiment Filter allows to filter out conversations where the customer displayed either contentment or frustration. Review tickets with negative sentiment to find areas for improvement. Or find conversations with positive sentiment to bring good examples or offer praise.
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 kinds of conversations result in unsatisfied customers.
How does it work?
Well, our feline mastermind Klaus is secretive about the specifics, but we use multiple state-of-the-art Natural Language Processing models to assign sentiment to messages. Neat, huh? (If you want an even shorter answer you can tell friends at parties: we use AI.)
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.
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.
Do you speak Cat?
We’re working tirelessly to make sure that the Sentiment Filter speaks your language. In addition to English, Klaus now recognizes sentiment in Portuguese, German, French, Dutch, Italian, Polish, and Spanish. Speak of multilingual superpowers! 🪄
Here’s how to get started:
You can simply create a new filter and add the rule ‘Sentiment is Positive/Negative’. This will show you all of the conversations where Klaus has found either delight or frustration.
The messages which have positive or negative sentiment are marked either with a green smiley face or a red frown face.
Let us know what you think!
As always, we’d love to hear what you think of the new feature. This helps us to improve the Sentiment Filter as well as the other upcoming AI features. Just get in touch right here in the chat.
