摘要：Little experimental research has investigated how attitudes are formed via direct personal experience within risky environments. This report summarizes the development of Treasure Island (TI), an attitude learning paradigm based on BeanFest. Two studies are reported: The first designed to compare the outcomes of TI with BeanFest; the second to show how a manipulation of risk predictability would affect attitude learning within the paradigm. Study 1 demonstrated sampling and learning asymmetries similar to those seen in BeanFest, although the magnitude of these asymmetries was attenuated by the opportunity for participants to landmark decisions. The manipulation of risk predictability in Study 2 led participants to seemingly form a less accurate representation of the underlying pay-off contingencies; however, a significant negative learning asymmetry did persist. The findings of this research (a) identify TI as a versatile paradigm for the investigation of attitude learning within risky environments and (b) confirm the robust nature of the negative learning asymmetry in contingent-learning settings; but (c) assert that care should be taken when generalizing the findings of BeanFest to ostensibly more variable contexts.
关键词：attitude formation; direct experience; BeanFest; contingent feedback
