Paper Number
ICIS2025-1967
Paper Type
Complete
Abstract
The abundance of online customer reviews hinders customers’ effective decision-making. AI-generated review summaries provide a promising solution, but their effectiveness largely depends on how they are designed and presented. Drawing on accessibility-diagnosticity theory, this study examines how three review summary designs (attribute block design, descriptive paragraph design, and composite display design) affect customers’ review reading performance. We further investigate two underlying cognitive mechanisms, product usage imagery and perceived product attribute diagnosticity, as mediators of these effects. Our experiment reveals that the composite display design, which integrates attribute blocks and descriptive paragraph, outperforms the other designs in enhancing customers’ review reading performance through both mediators. Specifically, product usage imagery facilitates the review reading process and promotes summary revisit behavior, while perceived product attribute diagnosticity strengthens review reading outcomes and increases add-to-cart behavior. This study contributes valuable theoretical and practical insights to the design and implementation of review summary features.
Recommended Citation
WANG, Guangxu; Xu, David (Jingjun); and LIAO, Stephen Shaoyi, "How Online Reviews Should Be Summarized via AI to Facilitate Review Reading" (2025). ICIS 2025 Proceedings. 21.
https://aisel.aisnet.org/icis2025/user_behav/user_behav/21
How Online Reviews Should Be Summarized via AI to Facilitate Review Reading
The abundance of online customer reviews hinders customers’ effective decision-making. AI-generated review summaries provide a promising solution, but their effectiveness largely depends on how they are designed and presented. Drawing on accessibility-diagnosticity theory, this study examines how three review summary designs (attribute block design, descriptive paragraph design, and composite display design) affect customers’ review reading performance. We further investigate two underlying cognitive mechanisms, product usage imagery and perceived product attribute diagnosticity, as mediators of these effects. Our experiment reveals that the composite display design, which integrates attribute blocks and descriptive paragraph, outperforms the other designs in enhancing customers’ review reading performance through both mediators. Specifically, product usage imagery facilitates the review reading process and promotes summary revisit behavior, while perceived product attribute diagnosticity strengthens review reading outcomes and increases add-to-cart behavior. This study contributes valuable theoretical and practical insights to the design and implementation of review summary features.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
16-UserBehavior