How the order of AI summaries shapes product opinions on Amazon
First Impressions: How Placement Shapes the Influence of AI Summaries
Human-Computer Interaction
Summary
People often see AI-generated summaries and user reviews when shopping online. This study found that both types of information change how people think about products, but the first thing they read has the biggest effect. Negative summaries influenced opinions more than positive ones, and only user reviews could change someone's mind after they saw a summary first. The researchers also discovered that people liked user reviews more but didn't realize how much the AI summaries affected their judgment.
What this means in practice
- •For e-commerce platform designers: Design product pages that consider how summary placement and order influence shopper opinions to encourage more accurate consumer judgments.
- •For online marketing teams: Tailor product information presentation order to maximize the impact of positive reviews and mitigate the effect of negative AI summaries on customer perception.
Authors
Wang Claire, Agam Goyal, Frederick Choi, Koustuv Saha, Eshwar Chandrasekharan
Abstract
AI-generated summaries increasingly mediate how people interpret information across platforms, including product reviews on e-commerce sites. Using Amazon's AI summaries as a case study, we conducted a preregistered, randomized experiment (N = 278) comparing how AI summaries and user reviews shaped product perceptions, and how their influence varied with valence and presentation order. We found that both AI summaries and user reviews influenced participants' opinions, with negative summaries having a larger effect than positive ones. Presentation order was the most important factor: the first source anchored judgment and only user reviews could displace an existing anchor. Although participants reported preferring user reviews, they often underestimated the influence of AI summaries on their judgments. Our findings show how the placement of AI summaries shapes user perception and highlight opportunities to design interfaces that support more deliberate judgments about when to rely on summaries and when to examine the underlying content directly.