Advanced computer recognition of aesthetics in the game of chess

Abstract

This research intended to see if aesthetics within the game of chess could be formalized for computer recognition since it is often appreciated and sought after by human players and problem composers. For this purpose, Western or International chess was chosen because there is a strong body of literature on the subject, including its aesthetic aspect. Eight principles of aesthetics and ten themes were identified. Flexible and dynamic formalizations were derived for each one and cumulatively represent the aesthetic score fur a move combination. A computer program that incorporated the formalizations was developed for testing purposes. Experiments were then performed comparing sets of thousands of chess compositions (where aesthetics is generally more prominent) and regular games (where it is not). The results suggest that computers can recognize beauty in the game. Possible applications of this research include more versatile chess database search engines, more accurate automatic chess problem composers, enhanced automatic chess game commentators and computational aid to judges of composition and brilliancy tournaments. In addition, the methodology applied here can be used to gauge aesthetics in similarly complex games such as go and generally to develop better game heuristics.