Home // ACHI 2023, The Sixteenth International Conference on Advances in Computer-Human Interactions // View article

An Experimental Study on Providing User Control in E-Commerce Recommendation through Conversational System

Authors:
Seth Owirodu
Yuchuan Lin
Sheng Tan
Zhou Tong

Keywords: Keywords—Recommender System; Conversational System; Transparency; User Control; E-commerce.

Abstract:
Recommender Systems(RS) are gaining importance across different domains, especially in e-commerce. Existing RS work mainly focuses on improving accuracy while neglecting other concerns associated with commercial RS, such as lack of transparency, little or no user control, and absence of diversity. In this paper, we aim to address those concerns by implementing a conversational system based e-commerce RS using real-world product data. We also conducted a month-long user study with over a hundred participants to investigate how users respond to the conversational system as a control mechanism to mitigate the abovementioned problems. Results show that the majority of the users give positive responses to the conversational system based control mechanism. The post-study questionnaires indicate that better control, transparency, and diversity can be achieved utilizing our system. By considering users’ perspectives, this work contributes to a better understanding of how we can utilize the conversational system to mitigate transparency and diversity issues associated with RS.

Pages: 85 to 92

Copyright: Copyright (c) IARIA, 2023

Publication date: April 24, 2023

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-68558-078-0

Location: Venice, Italy

Dates: from April 24, 2023 to April 28, 2023