It is no secret that telecommunications companies, which include wireless phone service providers, Internet service providers, and pay TV providers, have faced significant challenges providing excellent customer service. Due to the sheer breadth of their offerings, the relatively technical nature of their products and services, and seemingly ever-increasing prices, it is no wonder that telecommunications providers as a group have traditionally received lower customer rating scores, compared with companies in other industries.
Qualtrics’ 2020 XMI Customer Ratings found that wireless providers had average customer ratings that fell into the “Okay” category, falling well short of industries such as fast food, streaming media, retail, and grocery.
One way to combat this problem is to deploy sentiment analysis in customer call centers. Sentiment analysis provides a window into how a customer is feeling (elated, frustrated, angry), which, when correlated with specific actions, can not only provide insight into how your customers are feeling about your product offerings, but also provide a window into the customer-facing strategies, tactics, and approaches that are resonating (or irritating) your customers. Most notably, angry or frustrated customers are more likely to switch to another provider that they perceive has empathy for their situation, and sentiment analysis can be used to identify specific periods within an interaction where customer empathy should be prioritized.
“As we all know, the biggest frustrations with telco services are getting routed to the menu from hell where you can’t get out of it—you can’t get to a live person, and not being able to resolve the issue with one phone call,” says Darin Gull, president and general manager of TRACI.net Communications Consulting & Solutions, a voice services and solutions provider based in Deerfield, Beach, Florida. “So, what the industry is doing right now is using a lot of AI to help improve that customer sentiment.”
Gull says that using artificial intelligence (AI) to search for phrases that point to customer sentiment (such as “I’m angry you don’t offer this feature,” or “Thank you, you saved me so much time,”) allows call centers to home in on the interactions and agents that are eliciting specific emotions, which can then be analyzed to improve agent performance, ensure compliance with rules and regulations, and better understand the root cause of customers’ feelings about the company.
Although deploying sentiment analysis takes times (Gull notes that setting up sentiment analysis programs takes time and requires ongoing monitoring and evaluation), it can yield several benefits.
Capture nuances in agent performance
Traditional call center key performance indicators (KPIs), such as average call duration or first call resolution, may not capture how effective agents are at actually providing great customer experiences. Longer calls, which may appear to indicate that an agent is having difficulty resolving an issue, may actually be the result of an agent showing empathy and developing a rapport with a customer, which could engender more customer loyalty. Conversely, simply looking at first call resolution as a metric may ignore warning signs, such as agents failing to listen to a customer’s full complaint, or agents rushing the customer off the phone. Sentiment analysis can be used to better understand the interactions between call center agents and to identify top performing agents or strategies.
Allow the company to quickly identify and focus on negative customer interactions
It is impossible to review every customer engagement. The use of sentiment analysis may help identify which calls had negative sentiment, allowing quality assurance (QA) evaluators to zero in on the agents and types of interactions that may have the most negative impact on the overall customer relationship.
Identify cross-selling and upselling opportunities
Sentiment analysis can also be used to identify positive sentiment, as well as situations in which the customer is demonstrating interest. By analyzing a customer’s sentiment throughout a call, and cross-referencing it with specific keywords or phrases, agents can identify the best opportunity within a call to cross-sell or upsell, identify phrases or words to which customers respond positively, and avoid phrases that hinder or shut down opportunities to drive additional revenue.
Cross correlate sentiment with other contact center KPIs
Sentiment data can also be used to identify correlations between agent actions and other key metrics, such as customer retention rate, average hold time, product line, and call duration. Sentiment analysis can provide additional color to better understand how products and services are received by the customer, and also identify they key drivers of both positive and negative sentiment.
All told, sentiment analysis can be a useful tool in understanding customer perceptions of both the CX function and the products and services offered. It can also help identify top- or bottom-performing call center agents, who often serve as the first—and last—line of defense against customer attrition. “Comcast has greatly improved their scores, and they are using this technology,” Gull says. “If you look at what Comcast’s customer satisfaction scores were two years ago versus where they are now, it’s a huge improvement and that’s kind of the proof in the pudding.”
Author Information
Keith Kirkpatrick is VP & Research Director, Enterprise Software & Digital Workflows for The Futurum Group. Keith has over 25 years of experience in research, marketing, and consulting-based fields.
He has authored in-depth reports and market forecast studies covering artificial intelligence, biometrics, data analytics, robotics, high performance computing, and quantum computing, with a specific focus on the use of these technologies within large enterprise organizations and SMBs. He has also established strong working relationships with the international technology vendor community and is a frequent speaker at industry conferences and events.
In his career as a financial and technology journalist he has written for national and trade publications, including BusinessWeek, CNBC.com, Investment Dealers’ Digest, The Red Herring, The Communications of the ACM, and Mobile Computing & Communications, among others.
He is a member of the Association of Independent Information Professionals (AIIP).
Keith holds dual Bachelor of Arts degrees in Magazine Journalism and Sociology from Syracuse University.
