CRM Special Report: Untapped Gold
Even with technology, analyzing open-ended survey responses still is a labor-intensive and complex process. Human speech, by its nature, is unstructured. Many words have several meanings, and there are countless ways to express a single idea. It is difficult to manually detect the semantic closeness of every possible pair of sentences as well as take into account possible spelling mistakes.
There are new technologies available that assist in categorizing text responses. New solutions combine manual techniques with advanced linguistic technologies designed to extract and classify key concepts from within survey text. Natural Language Processing (NLP) technologies analyze text as a set of phrases and sentences in which the grammatical structure provides a context for the meaning of the text response.
This linguistics approach equates terms that are used in similar contexts. For example, NLP would equate terms like “executive,” “manager,” and even “mgr,” if they are used in similar contexts, whereas a non-linguistics-based solution may not equate manager with executive if it weren’t specifically stated. In addition, NLP technologies can interpret the tone of text. A customer comment about “new phone” may be distinct from a related concept, “new phone ASAP” response. The understanding of context cuts through the ambiguity of text, making linguistics-based text analysis the most accurate approach.
Technologies, like linguistics-based analytic software, are making it easier for direct marketers and researchers to pan for the gold in open-ended survey responses. The ability to personalize offers and better understand customers is a key factor in successful direct marketing. And, the best way to find out what is in customers’ heads, is to ask them.
Jason Verlen is vice president, survey applications business center at SPSS Inc. He can be reached at email@example.com.