Semantic search engine aims to improve health searches

Semantic Web search engine Hakia is putting a new twist on health searches by including credibility as one of the primary criteria for the search results it returns for health-related queries.

Hakia unveiled an update to its beta search engine today that will include search results that have been certified as being credible for health related searches as opposed to just results ranked on their popularity. As part of the update, Hakia will be providing results from Web sites that have met the quality criteria outlined by the Medical Library Association (MLA).

For example, when a user types the query “What are the benefits of aspirin?” Hakia will use MLA’s list of approved Web sites to provide results in addition to using other criteria like the most up-to-date information and the most relevant results, the company said.

While more than 100 million people search online for health-related information, 30% of searchers have concerns about the quality of the information, according to Forrester Research.

Credible health sites as determined by MLA include those run by the World Health Organization, the Centers for Disease Control, the National Cancer Institute, Mayo Clinic, American Cancer Society, the American Heart Association and the March of Dimes. The MLA is a nonprofit group that aims to promote quality health care information.

For all of its searches, instead of indexing search results based on the words found on a Web page, Hakia uses a technique to bring back more relevant search results by analyzing individual Web pages for bits of information like dates, names, events and other pieces of relevant information.

The technology is the brainchild of founder and CEO Riza Berkan, who spent much of his career using artificial intelligence to classify documents related to the country's nuclear weapons programs while working for the U.S. Department of Energy. Berkan has positioned Hakia as a search engine that can better interpret the user intent behind a user’s queries that those search engines that merely use key word analysis to bring back results.