Online flea market apps have become popular, particularly in Japan, as a means for individuals to sell used items to other individuals. The process of listing an item to be sold involves sellers uploading photographs and writing a product description to be viewed by potential buyers. Reducing the sellers’ workload during the item listing process has recently emerged as one application area for human-AI collaboration by leveraging Large Language Models (LLMs) in product description writing. In this research, we explore how LLM-based support may impact the experience of sellers and the listing price of items, as well as the subjective impressions and preferences of buyers regarding the attractiveness of human-AI collaboratively written item descriptions. The research results contribute to our understanding on how LLM-based tools may impact online second-hand markets, and provides insights on design considerations and future research directions for developing human-AI collaborative writing systems for flea market apps.

Miyuki Fujiwara, Rintaro Chujo, and Ari Hautasaari. 2025. Exploring Human-AI Collaborative Writing of Product Descriptions on Online Flea Market Apps from the Sellers’ and Buyers' Perspectives. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '25). Association for Computing Machinery, New York, NY, USA, Article 246, 1–6. https://doi.org/10.1145/3706599.3719718

Miyuki Fujiwara
is a Researcher in mercari R4D at Mercari, Inc. Her research interests include reading comprehension, semantic vocabulary, and computer-mediated communication in online C2C markets.

Rintaro Chujo
is a Ph.D. student at the Graduate School of Interdisciplinary Information Studies at the University of Tokyo. His main research area is Human-Computer Interaction and Computer-Supported Cooperative Work based on experimental psychology.

Ari Hautasaari
is a Project Associate Professor in the Interfaculty Initiative in Information Studies at the University of Tokyo. His research interests are in multilingual and socio-emotional computer mediated communication (CMC), computer-supported cooperative work (CSCW), and emotional value exchange in online C2C markets.

This research is part of the results of Value Exchange Engineering, a joint research project between R4D, Mercari Inc., and the RIISE.