How to Measure Customer Emotion

There are two ways to measure customer emotion in the contact centre. These include a survey-based metric and sentiment analysis.

METHOD 1 – The Survey-Based Metric

The survey-based metric is commonly known as Net Emotional Value (NEV).

Calculating Net Emotional Value (NEV)

When we visited AO’s contact centre in Bolton, we learned that the company ask their customers to describe their latest interaction with an advisor in just one word, via a text message after the call.

AO then categorise the responses that they receive into negative, neutral and excellent. By doing so, the company have all the information they need to calculate a NEV.

The responses that the customers give will represent an emotion that they felt during the call and – after eliminating neutral responses, such as “fine” – the contact centre can simply subtract the number of negative responses from the number of positive replies to get a NEV score.

Excellent (+ve)	Happy (+ve)	Indifferent (neutral)	Unhappy (-ve)
Ace	Attentive	Accommodating	Confused
Amazing	Bubbly	Alright	Disappointing
Awesome	Capable	Apologetic	Frustrating
Beautiful	Caring	Average	Poor
Brilliant	Charming	Calm	Rubbish
Delightful	Cheerful	Competent	Rude
Excellent	Considerate	Efficient	Terrible
Exceptional	Cool	Fine	Unhelpful
Exemplary	Courteous	Obliging	Unreliable
Extremely helpful	Effective	Ok	Unsatisfactory
Fabulous	Empathetic	Satisfactory	Useless
Fantastic	Enthusiastic	Useful
First-class	Friendly
Gorgeous	Good
Incredible	Great
Legend	Happy
Magnificent	Helpful
Marvellous	Informative
Outstanding	Kind
Perfect	Knowledgeable
Sexy	Lovely
Smashing	Nice
Spectacular	Patient
Splendid	Personable
Star	Pleasant
Super	Polite
Superb	Positive
Supercalifragilistic-expialidocious	Professional
Terrific	Proficient
Tremendous	Reassuring
Wonderful	Sound
	Supportive
	Sympathetic
	Thorough
	Understanding
	Very efficient
	Very good
	Very helpful
	Very nice

(These are some examples of words sent to AO’s contact centre in Bolton)

The equation for a Net Emotional Value (NEV) is shown below.

This NEV score could end up being positive or negative, although the aim is to get it to be as high as possible.

A different contact centre could choose for advisors to ask customers the question over the phone at the end of the call, to boost response rates, instead of sending a text message. However, this could distort the overall NEV score, as the customer may hide their dissatisfaction from the advisor who took the call.

So an automated IVR survey once the call has come to an end could be a better alternative.

The Benefits of Using This Method

It can be used on an individual advisor level – While it is useful to track the general emotion of customers leaving the contact centre, each individual advisor can be given a NEV score based solely on the conversations that they have with customers. This can be useful to highlight those who need more coaching, as well as those who deserve reward and recognition.

It tells you what is working and when – The NEV can also be used in isolation on certain call types, so the contact centre can track which contact reasons are causing the most negative emotion. Also, as the metric changes constantly with every new piece of feedback, the contact centre can ascertain immediate feedback when a process or introduced.

It is much cheaper than sentiment analysis – Sending an automated text or IVR message is a great deal easier than finding the funds for the analytics solutions required for sentiment analysis.

For more examples of positive words in customer service, read our article: Top 25 Positive Words, Phrases and Empathy Statements

METHOD 2 -Sentiment Analysis

Calculating Emotion Using Sentiment Analysis

Sentiment analysis combines both the acoustic characteristics of a speaker’s voice and the context of the conversation into a single score. This call score can be used to measure relative sentiment or emotion across various cross-sections of calls, advisor groups, and time frames.

According to Frank Sherlock, VP International at CallMiner, “sentiment analysis allows for a more objective interpretation of factors that are otherwise difficult to measure or typically measured subjectively, such as:

• The amount of stress or frustration in a customer’s voice (measures micro-tremors)
• How fast the individual is speaking (rate of speech)
• Changes in the level of stress indicated by the person’s speech (such as in response to a solution provided by a customer support representative).”

To do this, the contact centre must have access to an interaction analytics system. This provides all the necessary features to analyse everything listed above and provides a scoring mechanism. The process is otherwise known as opinion mining.

The Benefits of Using This Method

It can measure emotion across 100% of interactions – The first method relies on survey responses, while this option allows the contact centre to assess 100% of customer calls. This allows for a more accurate assessment of what is happening on the contact centre floor.

It can detect sarcasm – If method one is used, there will be those who send in a text message to say that their advisor interaction was “fantastic”, but mean it in a sarcastic manner, which is impossible to interpret. However, sentiment analysis can often detect sarcastic tones during the conversations.

It can automatically deliver advice to advisors – Sentiment analysis can run in real time and programmed to provide live feedback to advisors, allowing them to respond appropriately to affect the outcome of the interaction.

It can flag individual calls for greater analysis – According to Tim Pickard, the Chief Marketing Officer at NewVoiceMedia, being based on an interaction analytics solution, sentiment analysis can “spot trends, flag individual calls for analysis and implement many other processes for improved quality assurance.”

It can detect subtle shifts in customer opinions – Just like the previous method, this can really have the contact centres voice of the customer. However, only sentiment analysis can monitor attitudes and opinions about products, services, or even customer support effectiveness. It’s even possible to detect subtle shifts in opinions and adapt processes to meet changing customer needs.

Why Is It Important to Measure Customer Emotion?

As we discussed in our article “How to Improve Your Emotional Connection with Customers”, emotion has been found to have a greater impact on customer loyalty than success or effort.

The fact is emotions matter in Customer Experience. They matter enough that every team should be working to evoke the right ones.

Colin Shaw

According to Colin Shaw, the Founder & CEO of Beyond Philosophy: “The fact is emotions matter in Customer Experience. They matter enough that every team should be working to evoke the right ones. However, unless you measure your progress, you won’t know if you are.

“The NEV or sentiment analysis can help you see what’s happening in your Customer Experience at an emotional level, and how to make it the competitive differentiator that you need it to be.”

Another point that Colin makes in his article Measuring Customer Emotion in the Customer Service is that while the Net Promoter Score (NPS) is still a great metric for measuring customer loyalty, it is limited in comparison to measuring a NEV.

“The NEV is the new way to define success for your Customer Experience. The NPS only tells you an overview of whether or not the customer approves of your Customer Experience.

“The NPS is still important. In fact, our research shows that when the NEV is high, the NPS is too.

“All this is to say that I don’t think any organisation should drop the NPS as their metric any time soon. I only suggest that they take their analysis to the next level with the NEV.”

Have you tried using either of these methods for measuring customer emotion? What were your experiences?

Please share your thoughts in an email to Call Centre Helper.

For tips on how to evoke positive emotions during customer-advisor interactions, read our article: 7 Ways to Build an Emotional Connection With Callers