LLMs as Scalable Tools for Interactive Consumer Behavior Experiments: Comparing Persuasion Strategy Effectiveness

Recent advances in large language models (LLMs) present an opportunity to addressmethodological limitations in traditional online experimental approaches. Here, wedemonstrate the value of LLMs as experimental tools for consumer behavior researchusing a case study on persuasion. We present two studies in which LLMs engage participants in back-and-forth conversations with the goal of shifting consumption-relatedattitudes. Study 1 examines which strategies are naturally employed by the LLM,and the effectiveness of these strategies, when persuading participants about smart-phones (iPhone versus Android). Study 2 experimentally manipulates which persuasivestrategy the LLM uses when persuading about meat consumption or online shopping(Amazon versus Walmart.com). Our results suggest that conversations with LLMs caneffectively shift both self-reported attitudes and actual behavioral choices, with factualand informational appeals proving particularly effective across outcomes. Conversely,overtly manipulative strategies–including social consensus appeals and bias framing–were less effective. Moderation analysis reveals that pre-existing trust in AI technologysignificantly enhances persuasive effectiveness, while mediation analysis identifies perceived AI manipulation and expressed skepticism as key psychological mechanismsunderlying consumer resistance. Beyond these substantive findings, our research thevalue of LLMs in experiments allowing for the efficient testing of multiple theoretical predictions within single experimental frameworks and bridges observational andexperimental paradigms through automated content analysis.