Anderson Analytics Founder presents “Mining Text in Guest Satisfaction Surveys: Do Ratings Truly Customer Intentions?” at SPSS Directions 2005 Conference in Las Vegas.

Las Vegas, NV November 20, 2005 — Dissatisfied with the lack of real data and emotional content in a numerical customer satisfaction survey? If a ‘9’ on a 10-point scale is really good, what is an ‘8’? Is there information from that ‘8’ that could help you improve and how can you get to it?

The answer is called text mining, and it works just like the miners did during the gold rush. Text mining allows the user to extract more from a numerical survey by “mining” the verbatims for patterns in responses and linguistic concepts. Nowhere does text mining for customer satisfaction make more sense than in the hotel industry, especially when the hotel is a global brand such as Starwood Hotels & Resorts.

This Friday, Tom Anderson of Anderson Analytics (www.andersonanalytics.com), a leading market research consultancy, presented “Mining Text in Guest Satisfaction Surveys: Do Ratings Truly Reveal Future Intentions?” and speak further about this cutting-edge form of research.

“Starwood Hotels and Resorts were delighted to participate in this text mining project. Understanding the key words that drive verbal satisfaction could provide another important tool for General Managers to ensure that a guest's stay is a great one,” said Rebecca Gillan, Senior VP, Market Research and Guest Satisfaction, Starwood Hotels & Resorts Worldwide, Inc. “Being better able to judge how satisfied a guest is while they are still at the hotel provides another opportunity to make the guest's experience a positive one, which is the most important factor in the decision to return to the hotel and ultimately to drive true preference for our brands.”

Most companies only analyze, and learn from, a small portion of the quantitative data they collect. Unfortunately, they do an even worse job of listening to the verbatim data they receive each day, either via emails, letters, phone calls, suggestion boxes, or even surveys. Every year millions of customer complaints, suggestions and even praise go unheard. The closest a company may come to actually analyzing what customers say is if they conduct dozens of focus groups with 1-12 respondents per group.

One area which Anderson Analytics has been exploring has been data mining and especially text mining. Tom Anderson, Founder and Managing Partner of Anderson Analytics said “We’re very excited to be involved in this brand new field which combines statistics, artificial intelligence, and machine learning. Projects like these are exactly why Anderson Analytics was founded. To go beyond the obvious and find ways to help our clients by digging deeper into the data”.

About Anderson Analytics
Anderson Analytics is a full service market research consultancy, providing quantitative and qualitative solutions. At Anderson Analytics we help solve challenging marketing problems and discover hidden opportunities. We combine the efficiencies and business experience found in large research firms with the rigorous methodological understanding from academia with the enthusiasm and creativity found only in smaller firms. Helping clients achieve a significantly better return on marketing investment is our main goal. For more information, please see www.andersonanalytics.com.