Improving Search with Behavioral Analyses

February 21, 2012

I wrote my KMWorld column about the interesting system and method developed by Dr. Linda McIsaac, president of Xyte, Inc. I learned about Xyte’s work in Washington, DC. A number of Federal entities tap her company for behavior-centric research.

I interviewed Dr. McIsaac on February 15, 2012, and the information I gathered struck me as important and highly relevant to enterprise search. With users of enterprise search systems expressing significant dissatisfaction with incumbent systems, licensing a new search engine should make people happy. Well, it does not. Traditional methods of figuring out what makes a user of a findability purr does not work particularly well.

Dr. McIsaac’s method may provide a solution. I have put the full text of our conversation on my Search Wizards Speak subsite. You can access the interview at this link.

Here’s an example of the outputs her research approach:

Xyte provides a system science model and a structure that identifies the way people function intellectually by classifying their cognitive information-processing capabilities presented as a logical system of relationships among various human capabilities. In simple terms, Xyte’s system provides a structure based on a proven theory which is predictive of the way individuals think and process information and then act consistently. No other system is predictive.

I was able to gather some information about the type of findings she delivers to clients. She told me:

Xyte surveyed each of what we call cognofiles or behavioral sets of the Xyting Insight™ system about usage of social media to determine who is most apt to use these computer applications. Not all consumers are eager to use Facebook or use it consistently. According a recent Xyte study, 27 percent of the population has never logged in to Facebook and another 20 percent only log in once or more a month. Data from our study suggest that some of the broad generalizations about social media, particularly as a replacement for a search system or face-to-face interaction are inaccurate. That means that advertisers are missing 47 percent of the population. However, 38 percent do log in daily and 16 percent do log in several times a week. The population segment that most frequents Facebook has a number of characteristics; for example, showing great compassion for others, wanting to be emotionally connected with others, having a natural intuition about people and how to relate to them, adapting well to change, embracing technology such as the Internet, and enjoying gossip and messages delivered in story form and liking to read and write.

For more information about Xyte, navigate to www.xyte.com. The complete interview is at http://www.arnoldit.com/search-wizards-speak/xyte.html

Stephen E Arnold, February 21, 2012

Comments

Comments are closed.

Search the site
Subscribe to Beyond Search
Feature archive
News archive

Stephen E. Arnold monitors search, content processing, text mining and related topics from his high-tech nerve center in rural Kentucky. He tries to winnow the goose feathers from the giblets. He works with colleagues worldwide to make this Web log useful to those who want to go "beyond search". Contact him at sa [at] arnoldit.com. His Web site with additional information about search is arnoldit.com.