Parsing customer comments

Swisscom employs text analytics to better understand customer concerns

When cable subscribers call Swisscom to report signal problems from their television screens, the operator quickly narrows down the problem, recommends a fix and describes what actions need to be taken. A customer’s email frustrated with service-option confusion can trigger the perfect offer without a marketer even needing to read the email.

The largest telecom provider in Switzerland achieves this rapid response to customer needs because of its investment in SAS® Text Analytics. “With text analytics it is possible, almost simultaneously with the ongoing call center documentation, to show relationships and provide solutions,” says Albert Labermeier, Senior Marketing Analyst at Swisscom. Instead of call center employees finding out weeks later that what a customer was describing was related to a bad Wi-Fi connection or a malfunctioning remote control, data is being analyzed daily to match problems to solutions. This arms the call agents with the right answer to the customer’s need – the first time.

We are able to create fully automated daily reports, which has a direct positive effect on service quality and customer satisfaction.

Albert Labermeier
Senior Marketing Analyst

Ending a slow, tedious process

Like many organizations with call centers, Swisscom manually documents the customer conversation as it’s happening. Historically, that detail was reviewed (manually) at specific intervals. With 10,000 daily incoming service requests, the manual process was simply not effective or productive, overwhelming staff and lacking timeliness – never being completed fast enough to make a difference. The company also had no fast way to know and respond to what customers were saying about the company and its products and services on social media.

Using SAS allows Swisscom to quickly and accurately filter out customer wishes from the noise of unstructured digital data volumes. The technology is deployed throughout the organization, including corporate communications and public relations.

Building on a marketing optimization base

Swisscom already was using SAS® Marketing Optimization to segment and automate marketing messages. By layering the insight from social media conversations with the analysis of call center transcripts and incoming inquiries, a richer picture of customer needs and issues has emerged. Now the company can make even more relevant and customized offers to help retain customers in the increasingly competitive telecom market. In the initial testing of SAS to analyze the unstructured text, the technical and business users worked together to identify keywords and create a dashboard that would deliver real-time information. The results impressed: “It convinced us right from the start,” Labermeier says.

But what really impressed the team was how the solution could help pick through diverse descriptions and synonyms and properly categorize them. The analysis needed to not only detect predefined keywords, but also automatically recognize that terms like “ants race,” “jolt” or “flicker” are all descriptions of image quality issues. Reports are now sent daily (instead of weekly or monthly), and staff members assign actions to descriptions – whether it is a repair, a replacement or an issue beyond Swisscom’s control. “This has a positive effect on service quality and customer satisfaction,” adds Labermeier.


Better understand customers and their concerns by automating analysis of call center conversations and social media commentary.


SAS® Text Miner
SAS® Sentiment Analysis


Problems that took weeks to identify and properly train call center staff to anticipate can now be identified in 24 hours. Marketing offers are fine-tuned for customer retention strategies, and call center staff members spend less time on administrative work and more time with customers.

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Back to Top