Finding people just got simpler on net

Birmingham Star (ANI) Thursday 16th October, 2008

Washington, Oct 16 : Managers would now be able to quickly find out which of their employee has previously worked on a project and whom to assign new responsibilities, thanks to a new computer program, developed by researcher Krisztian Balog.

The new computer program will make it quicker and easier to look for a specific person in an organisation's network.

The new technique would also make it easier to find the right person on the Internet on the whole.

While it is easier to search for documents, it gets difficult when it comes to searching for people.

Thus, focussing mainly on finding people within companies and organisations, Balog has introduced two new models in his thesis that make finding the right person quicker and more accurate.

In the business world, an effective search system can be used, for example, in helping a manager to quickly find out who had previously worked on a certain project.

In fact, the system can also ensure a better exchange of information between companies and the press or between companies and employment agencies. For example, an HRM department can use the search system to find out more about job applicants.

The PhD thesis mainly deals with two methods of information disclosure-compiling a list of experts for a subject and making a list of subjects per expert.

While text format can make it easier to find documents, a person cannot be found in the same manner. But, a person also leaves a digital trail because his or her name can be found in the texts.

The new method uses these digital traces to compile a list of subjects for a person and the program accordingly selects the person that can satisfy the criteria of the search query.

For developing the program, Balog combined so-called generative language models with learning algorithms. While the language models expose patterns in the language use with respect to persons and subjects, learning algorithms recognise people and organisations in texts.

The model can also process many different types of search queries and is, therefore, highly flexible. A journalist can even use the system to determine how high environmental issues are on the agenda of a political party.