说服
聊天机器人
对话
心理学
认知
认知心理学
社会心理学
知识管理
知识流
领域知识
计算机科学
知识共享
知识水平
描述性知识
对话系统
互联网
流量(数学)
精化可能性模型
知识库
动作(物理)
说服性沟通
作者
Sein Kim,Hayeon Kim,Sang Woo Lee
标识
DOI:10.1080/10447318.2026.2728933
摘要
Conversational AI is rapidly expanding in e-commerce, where chatbot questions critically shape users’ cognition and engagement. Yet, the effects of question timing and type on persuasion remain underexplored. Building on the persuasion knowledge model, this study examines how question timing (in-conversation vs. follow-up) and type (informational vs. experience-evoking) influence users’ knowledge structures, flow experience, and purchase intention. We developed a retrieval-augmented generation-based recommendation chatbot and conducted an online experiment with 335 participants. The analysis showed that informational questions presented during the conversation and experience-evoking questions presented as follow-up prompts strengthened topic knowledge. Persuasion knowledge was most strongly activated when experience-evoking questions appeared during the conversation, whereas agent knowledge varied depending on the timing–type combination. Topic knowledge positively predicted flow components and purchase intention, whereas persuasion knowledge negatively predicted these outcomes. Agent knowledge was activated under certain question configurations but did not directly predict flow experience or purchase intention.
科研通智能强力驱动
Strongly Powered by AbleSci AI