EDS is an IT services company with 120,000 employees operating in 60 countries. Under new leadership since 2003, the company is pursuing aggressive goals in four areas: account operations, product mix, financial performance, and organizational effectiveness.

As a services company, EDS people are the key element of the company. Whereas software, hardware, and systems companies offer value mainly through products, services companies like EDS serve clients through people. The knowledge, skill, and experience of employees are the lifeblood of the company. As such, all corporate goals have important workforce components, such as change management and continuous re-skilling. In addition, maintaining the values of the company is an ongoing workforce priority.

Central to maintaining an effective workforce, is employee feedback. EDS leaders use a variety of forums to engage in constant dialog with employees. One mechanism for feedback is the EDS employee survey program.

The EDS survey program includes an annual survey, the Voice of the Employee (VOE) survey, in which all employees world-wide are invited to participate. Additional surveys are implemented three to four times a year. Called Pulse Surveys, these additional surveys are sent to stratified samples of employees across the company.

Historically, employees were providing responses to scaled questions on surveys, which delivered quantitative results along several variables such as leadership, communication, and the work environment. This data was analyzed and interpreted using traditional tools.

Since 2003, open-ended questions have been added to employee surveys. Text generated from open-ended questions offers a broader, richer source of information than do scaled questions alone.

Unstructured text data, of course, presents new challenges as well. Initially, text comments from open ended questions were processed manually. Teams of employees reviewed the text then coded each record into one or more topics. Inter-rater reliability was maintained by having several employees code a portion of the text, then comparing the results. After the coding process, summaries and examples were created and reported to EDS senior leaders for follow-up action.

While the value of text comments for improving organizational effectiveness was unquestioned, two problems persisted. First, the process was slow. Whereas survey reports of quantitative survey data were available a few weeks after a survey closed, text comment reports lagged by months. Moreover, the process at times involved more than a dozen employees. From a productivity standpoint, the slow, manual process could not be sustained.

Second, the manual coding process was difficult to adjust to varying situations. For example, if a topic became too broad to be meaningful (e.g. “unit-level communication”), a principled subdivision was difficult to achieve. At the other extreme, a single, widely-distributed comment (e.g. “many emails contain redundant information”) was difficult to link to higher-level topics.

By 2005, EDS survey analysts set three high-level goals for analyzing text comments. First, cycle time must be reduced to allow text and quantitative data to be reported at the same time. Second, the resource requirement must reduce from dozens of employees to one person. Third, the new approach must be scalable to a wide variety of projects.

To view the full document, please download the PDF: Full Nomination (PDF)