Product recommendation method based on commodity aspect emotion mining and fuzzy decision

The invention relates to the technical field of Internet, in particular to a product recommendation method and device based on commodity aspect emotion mining and fuzzy decision making, computer equipment and a storage medium, and the method comprises the steps: obtaining comment data of each to-be-sorted commodity, and extracting all feature word-viewpoint word pairs corresponding to each attribute from the comment data; based on the positive and negative emotional tendencies of each feature word-viewpoint word pair, calculating an interval type Pictgomery fuzzy number on each attribute of each commodity to form an emotional decision matrix; utilizing a Heronian operator to establish a comprehensive emotion decision matrix, preference of the user for each attribute and a scoring model ofcorrelation among the attributes; and obtaining a scoring result of each commodity by utilizing the scoring model, and sorting the commodities according to the scoring results. According to the method, by analyzing online com