Have you always been wondering what customer sentiment analysis stands for? Let’s get to the bottom of it. But first, let’s set some context.
Customers want positive experiences. Brands do too!
“People will forget what you said, people will forget what you did, but people will never forget how you made them feel”
This powerful quote by Maya Angelou explains why we feel so passionately positive about some brands and so strongly negative about others. A Mckinsey study has shown that brands try hard to evoke positive emotions for a reason: Feelings are strongly correlated with profits! After a positive customer experience, more than 85 percent of customers purchased more, and after a negative experience, more than 70 percent purchased less.
Collect and act on NPS-powered customer feedback in real time to deliver amazing customer experiences at every brand touchpoint. By closing the customer feedback loop with NPS, you will grow revenue, retain more customers, and evolve your business in the process. Try it free.
Any company owner would love to know:
How can they make customers feel positive or negative?
Who are the customers who had particularly negative experiences? Why, and how can they help them?
How can they engage customers who are indifferent?
One of the ways to find the answers to these questions is to collect customer feedback. And while making sense of it isn’t easy, it is certainly worthwhile.
What is customer sentiment analysis?
Customer sentiment analysis determines how customers feel based on their language. The basic idea is that strong feelings lead to emotionally laden words. Algorithm creators use this information to figure out two parameters: Sentiment polarity shows whether the feelings are positive or negative. Sentiment magnitude shows how strongly customers feel.
The algorithms determine customer sentiment using one of these two approaches:
Dictionary: Look up polarity and magnitude given the word or phrase. Reverse if there is a negation.
Categorisation: Learn from examples how to categorise any new piece of text using Machine Learning.
If you are wondering how algorithms handle sarcastic comments, such as “I love to wait hours until my dinner arrives”, the short answer is they don’t. The long answer is in our related post on sarcasm in customer feedback.
How companies can benefit from customer sentiment analysis
Google has been innovating in customer sentiment analysis for many years. Here is how they presented online shops in their search a while back:
Both the shop itself, Dick’s Sporting Goods, and their potential customers can see an overview of what’s good, what’s lacking. The selection looks good: Customers will find it easier to find the right product, and the shop could emphasise this in their marketing. Return policy and customer service are lacking: Customers will feel that the purchase will be risky, and these are the two areas the shop should improve.
Strategic insights based on customer feedback
Modern customer sentiment analysis solutions can provide deeper insight than this. They can capture what specifically people don’t like about the return policy, and after the business has taken steps to fixing the issue, or improving a process, they can track how that has improved customer satisfaction. They can also differentiate between feedback that is frequent and feedback that influences satisfaction scores.
Operational improvements based on customer feedback
Customer sentiment analysis can help brands in a more actionable way. It can pick out from large volumes of feedback which customers need extra care. They may be mentioning issues such as making a payment, repeated frustration with the call centre, or intention to cancel the service. Tracking such themes and introducing required processes is the key when it comes to closing the loop: from receiving feedback to figuring out which action will result in a positive customer experience.