Paper Number
ICIS2026-2524
Paper Type
Completed
Abstract
Conversational agents are becoming integral to e-commerce, reshaping how consumers search, compare, and purchase products. As large language models (LLMs) advance, companies increasingly integrate conversational assistants into online shops, creating hybrid interfaces that combine chat with traditional search, filter, and navigation elements. Yet, it remains unclear how such designs influence user behavior and decision-making. In the problem awareness phase of a design science research (DSR) project, we reviewed existing conversational shops and developed a hybrid conversational shop prototype featuring an LLM-based assistant for white goods. Using attention allocation theory and the theory of effective use, we examined the prototype’s impact in a mixed-method study involving eye-tracking, behavioral metrics, subjective assessments, and interviews. Findings indicate that conversational shopping reduces efficiency but maintains effectiveness compared to traditional shops. The paper contributes design knowledge for this emerging problem space and proposes five design requirements for creating conversational online shops that support effective use.
Recommended Citation
Feick, Martin; Langner, Moritz; Schelhorn, Till Carlo; Kaiser, Carolin; and Maedche, Alexander, "When Online Shops Start Chatting: Exploring Design Requirements for Conversational Online Shops" (2026). ICIS 2026 Proceedings. 21.
https://aisel.aisnet.org/icis2026/user_engage/user_engage/21
When Online Shops Start Chatting: Exploring Design Requirements for Conversational Online Shops
Conversational agents are becoming integral to e-commerce, reshaping how consumers search, compare, and purchase products. As large language models (LLMs) advance, companies increasingly integrate conversational assistants into online shops, creating hybrid interfaces that combine chat with traditional search, filter, and navigation elements. Yet, it remains unclear how such designs influence user behavior and decision-making. In the problem awareness phase of a design science research (DSR) project, we reviewed existing conversational shops and developed a hybrid conversational shop prototype featuring an LLM-based assistant for white goods. Using attention allocation theory and the theory of effective use, we examined the prototype’s impact in a mixed-method study involving eye-tracking, behavioral metrics, subjective assessments, and interviews. Findings indicate that conversational shopping reduces efficiency but maintains effectiveness compared to traditional shops. The paper contributes design knowledge for this emerging problem space and proposes five design requirements for creating conversational online shops that support effective use.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
14_User_behavior