A Guide to Contact Centre Sentiment Analysis

Tammy Marinac of Calabrio introduces us to sentiment analysis and the art of measuring emotion in the contact centre.

If you’re like me, you’ve misinterpreted more than your fair share of text messages because you couldn’t determine the intended emotion behind the words. Was the sender being serious? Sarcastic? Flippant? Unless you know the person – and their use of emoticons – figuring out what they really mean can be dicey.

Contact centre analytics can run into the same type of issue when analysing a customer call. It’s not enough to analyse and understand what customers say – the software also needs to understand what the customer means.

Most organisations don’t do a great job of holistically ascertaining customer sentiment. And if they rely solely upon common tools such as surveys and focus groups, they’re only targeting a minute proportion of the population and will never be able to truly understand customer satisfaction levels.

The good news is that the tide is turning. With the rising importance of voice-of-the-customer (VoC) data, contact centres are in a unique position to decipher both meaning and context from customer interactions. Thus, sentiment analysis is a powerful tool that call centre managers and customer experience leaders can use to learn more about their customers.

What Is Sentiment Analysis? How Does It Work in the Call Centre?

Sentiment analysis not only tells you your contact centre’s overall sentiment score, it also adds contact centre workforce optimisation (WFO) suite KPIs to correlate sentiment with metrics like call duration, hold time, silence, evaluation score and Net Promoter Score (NPS) to allow you to identify trends that until now may have gone unnoticed.

Sentiment analysis creates a scorecard that brings together both the WFO and the workforce engagement management (WEM) picture. All the utterances in a call are analysed to give each call a sentiment score of positive, negative or neutral. By looking at this dashboard, call centre managers can spot trends in call sentiment and can often identify issues before other KPIs like sales or NPS drop.

5 Benefits of Sentiment Analysis in the Contact Centre

When your contact centre uses sentiment analysis along with your call recording software, you no longer need to manually monitor calls or study interaction transcripts to find out how customers feel about your business.

Here are five of the top benefits of sentiment analysis:

1. Capture agent effort often overlooked in typical performance metrics

KPIs like call duration don’t always tell you how effective your agents are. For example, a longer call can sometimes mean that an agent is adept at handling complex issues. You can use sentiment analysis to identify the agents consistently involved with calls that have positive sentiment so you don’t miss out on rewarding – and learning from – your top agents.

2. Send QM evaluators down the right path

Your evaluators don’t have time to listen to every call to monitor for quality. Sentiment analytics is able to help identify the agents involved with calls that had negative sentiment – which gives your evaluators a better idea of where to start their reviews.

3. Supplement post-call surveys to amplify voice of customer

Don’t rely on the small percentage of customers who respond to survey requests to learn how your customers feel about your brand. Instead, you can supplement your survey and focus group results with sentiment analysis data so you understand the impact of every interaction.

4. Test effectiveness of marketing campaigns

Marketers can use sentiment analysis to discover how customers view their most recent ad campaigns, home in on the most effective marketing messages, find out how customers view their brand or understand how customer sentiment varies by product line.

5. Quickly identify root causes

By pulling sentiment data into your everyday contact centre KPI reports, you can identify correlations that might not be obvious. For example, you can view a line chart showing your rate of customer retention alongside the number of calls with negative sentiment. Then listen to only those calls that are negative in sentiment and correlate with a decrease in retention to find out why customers are leaving you.

Questions That Can Be Answered Using Sentiment Analysis

• Are longer calls more likely to be associated with happier customers or with customers who view the company negatively?
• How does sentiment correlate to specific agents, groups or teams that consistently generate high or low customer satisfaction?
• How do my customers feel about my most recent ad campaign?
• How does customer sentiment vary by product line?
• What are the top phrases that consistently get used during calls with positive sentiment? Or those with negative sentiment?
• Which day of the week tends to have the most positive sentiment? Which day tends to be the most negative?
• Have there been recent shifts in customer sentiment levels?

Case Study: How Sentiment Analysis Provides Business Value

Let’s look at a real-world example. A furniture retailer in North America turned to Calabrio Sentiment Analysis to better understand how their customers’ satisfaction varied by product. They evaluated the sentiment of all 49 of their product lines and found that the product with the most positive sentiment score was a line of coffee tables. This was a surprise to them because, to date, the sales numbers for those tables had been only average.

They learned from sentiment analysis, however, that customers who owned this particular coffee table were overwhelmingly positive during their interactions with the contact centre. The retailer dug into the interactions to find out why – and they learned that customers loved how well the table held up over time and that the table’s finish “never chipped”.

The retailer used this insight to revamp the way they positioned the coffee table in their stores and on their website. Now when customers walked into a store or viewed the company’s home page, the “never chipping” coffee table was front and centre – along with new messaging that highlighted the strength of the table’s finish.

And the retailer’s sales went up! Prior to their analysis of customer satisfaction by product line, sales of the table had been flat and relatively average compared to other lines of products. But after they found out how much (and exactly why) customers loved the table, they could change their website and store layouts to better highlight the product’s strengths. The result was an increase in sales to the tune of $400,000.

What to Look for in a Contact Centre Sentiment Analysis Solution

Traditional processes and legacy tools for understanding customer sentiment are tedious and unreliable, often preventing businesses from seeing a complete customer picture – the opposite of what you want to achieve.

Instead, you want quick, accurate and meaningful customer engagement metrics and automatically updating customer sentiment metrics that you can access via dashboards and customisable reports.

Here are six questions you should ask when evaluating a contact centre sentiment analysis solution:

1. Is this solution specifically attuned to sentiment expressed within contact centres?

Nearly every call into a contact centre occurs because the customer has an issue they need solving – but that doesn’t mean that every interaction will have a negative sentiment. The right solution will recognise that contact centre conversations are unique.

2. Can it detect negation?

Most contact centre analytics solutions can’t tell the difference in sentiment between the phrases; “That was a terrible response” and “I did not love that response”. The right solution will take a holistic approach that doesn’t base sentiment analysis around a single word or phrase and so can accurately detect the negative sentiment of both statements.

3. Are manual efforts required?

You’re more likely to take advantage of contact centre sentiment analysis if it’s easy to use and access results. You’ll want to look for a fully automated solution that delivers sentiment scores directly to your dashboard or report without the need to spend valuable time on manual examination.

4. Does it enable targeted quality management?

The best solution will deliver the names of top-performing agents, teams and groups in terms of sentiment so you can easily enable sharing of best practices – and it will serve as a leading indicator in terms of identifying agents who need manual quality evaluations.

5. Does it allow you to correlate sentiment scores with other contact centre KPIs?

The right solution will not only tell you the overall sentiment score for your contact centre, but it will also allow you to easily slice and dice sentiment data by key metrics like call duration, average hold time, product line or retention rate – and to marry sentiment info with customer and agent effort scores.

6. Is it accurate?

Look for a solution that leverages machine learning and best-in-class speech analytics engines to deliver sentiment analysis accuracy rates that statistical benchmarking reveals to be more accurate than tools that include IBM Watson.

You’ll also want to look for a solution that makes it easy to analyse and report on the results. Top sentiment analysis solutions give you the ability to:

• Use them out-of-the-box with no need for configuration or to set up any tasks
• View sentiment trends over time
• Set filters you can use to view sentiment by agent, teams or groups, or apply to any other of your commonly used contact centre KPI reports
• Customise reports and dashboards to meet the needs of your contact centre
• Export data into other existing reports or analysis
• Drill down by simply clicking on reports or dashboards to view data details
• Amplify the voice of the customer and secure business decision buy-in more quickly

Sentiment analysis can help companies speedily identify unhappy consumers, gain essential insight into customer perceptions of its brand, product, operations and agent performance, receive automated, straightforward and accurate analysis of customer attitudes, and promptly identify root causes of concern and mitigate problems before they undermine the bottom line.

Author: Robyn Coppell