A new technology called RevRank, especially suitable for ranking product reviews according to the particular needs of the person performing the search, has been presented by Yissum Research Development Company, the technology transfer arm of the Hebrew University of Jerusalem.

This novel method for content analysis is specifically designed to automatically rank book and product reviews according to their estimated helpfulness.

Invented by Professor Ari Rappoport and Mr. Oren Tsur from the Hebrew University’s School of Computer Science and Engineering, RevRank first identifies a core of dominant terms that defines a virtual optimal review, and then uses those terms to rank other reviews relative to the ‘virtual core’ review.

“This novel method… allows us to easily identify the most helpful reviews on various topics, and, in the future, will actually generate one comprehensive, optimized review from the available data. It offers a necessary tool for coping with the vast amount of data in the web world,” says Yaacov Michlin, CEO of Yissum.

RevRank was successfully tested on book and product reviews on Amazon. As a result, effective reviews that had a good chance of being missed by readers were moved up to top positions.