Computer search engine thwarts terrorism

USA Today (Society for the Advancement of Education), Sept, 2005

As part of an effort to anticipate--and thwart--the plans of potential terrorists, the Federal Aviation Administration is supporting the development of a new search engine by University at Buffalo (N.Y.) scientists that is designed to detect "hidden" information that can be gleaned from public websites.

The system permits users to find the best trail of evidence through many documents that connect two or more apparently unrelated concepts. Existing search engines process individual documents based on the number of times a key word appears. In contrast, the new system is based on the construction of concept chain graphs that search for the best path connecting two concepts within a multitude of documents.

With regular searches, the input is a set of key words. The search produces a ranked list of documents, any one of which could satisfy the query. On the other hand, this engine is a composite query, designed to find the best path, the best chain of associations between two or more ideas. It returns to the user an evidence trail that says: This is how these pieces are connected.

To develop the method, the researchers used the chapters of the 9/11 Commission Report to establish concept ontologies--lists of terms of interest in the specific domains relevant to the researchers: aviation, security, and antiterrorism issues.

Eventually, the search tool also may be used for other applications, such as helping biomedical researchers conduct more effective investigations into the connections among genes, proteins, and disease.