摘要：In Experiment 1, 36 subjects were exposed to a stimulus equivalence procedure during which they were trained to match the two nonsense syllables VEK and ZID to the emotive words CANCER and HOLIDAYS, respectively, and to match the product labels BRAND X and BRAND Y to the nonsense syllables. The subjects were then tested for equivalence responding (e.g., CANCER --> BRAND X, and HOLIDAYS --> BRAND V). Finally subjects were presented with two samples of the same cola-based drink, one labeled BRAND X and the other labeled BRAND Y. Subjects were required to rate the colas for pleasantness. A significant difference in terms of the ratings of the pleasantness of the colas was found for the group who passed the equivalence test. The group of subjects who failed the equivalence test showed no significant difference in their ratings of the colas. Experiment 2 demonstrated that exposure to the equivalence test was not a prerequisite for the transfer of preference functions. Experiment 3 demonstrated that it is possible to reverse subjects' preferences for the two colas by reversing the trained conditional discriminations. Furthermore, unlike the previous two experiments, Experiment 3 assessed the preference functions for the emotive words before and after the conditional discrimination training and transfer testing.
