看见不等于感知：合成消费者何时能且不能预测试视觉营销
Seeing Is Not Perceiving: When Synthetic Consumers Can and Cannot Pretest Visual Marketing
浏览论文内容
中文总结 AI 辅助
本研究通过六个视觉营销实验检验生成式AI合成消费者预测试的可靠性，发现多数配置无法复现人类效应，并提出了校准、干预、部署的AI治理协议。
中文摘要 AI 辅助
营销人员现在部署生成式AI智能体作为合成消费者，以人类小组成本的一小部分来预测试视觉资产，如标志、包装和广告。然而，这一过程假设模型看到视觉线索也能感知其消费者含义，而这一假设在很大程度上未经检验。我们使用六个经典的视觉营销实验来压力测试这一假设，并改变管理者控制的两个杠杆：模型代际（GPT-4o-mini与GPT-5.4-mini）和输入格式（纯文本与JSON）。每个生成的配置都通过了操纵检查；然而，没有任何配置能重现六个人类效应中的两个以上，其余效应均不显著。唯一的例外是人类模式出现显著逆转。通过上下文学习提供概念性或经验性证据，可将平均响应导向人类效应。然而，引导存在局限：即使成功，配置也只能重现人类响应自然分布不到一半的变异，因此低估了消费者异质性。我们将这些结果整合到一个AI治理协议（校准、干预、部署）中，该协议界定了合成消费者何时能负责任地筛选创意作品，以及何时仍需人类小组。
英文摘要
Marketers now deploy generative AI agents as synthetic consumers to pretest visual assets such as logos, packaging, and advertising at a fraction of human-panel cost. However, this procedure assumes that a model seeing a visual cue can also perceive its consumer meaning, which is largely untested. We stress-test the assumption using six canonical visual marketing experiments, varying the two levers managers control: model generation (GPT-4o-mini vs. GPT-5.4-mini) and input format (plain text vs. JSON). Every resulting configuration passed the manipulation checks; however, none of the configurations reproduced more than two of the six human effects, and the remainder were nonsignificant. The one exception was a significant reversal of the human pattern. Providing conceptual or empirical evidence through in-context learning steers average responses toward the human effect. Yet steering has a limit: even when it succeeds, a configuration reproduces less than half of the natural spread of human responses and so understates consumer heterogeneity. We integrate these results into an AI governance protocol (Calibrate, Intervene, Deploy) that delineates when synthetic consumers can responsibly screen creatives and when human panels remain necessary.
发表机构
- The University of Melbourne（墨尔本大学）
机构由 AI 辅助整理，请以论文原文为准。
