Analysing the effectiveness of chatbots as recommendation systems in fashion e-commerce: a cross-cultural comparison

Landim, André R.D.B., Moura, Antão, Vieira, Thales, Wanick, Vanissa and Bazaki, Eirini (2024) Analysing the effectiveness of chatbots as recommendation systems in fashion e-commerce: a cross-cultural comparison. 2024 GLOBAL FASHION MANAGEMENT CONFERENCE, , Milan, Italy. 11 - 14 Jul 2024. (In Press)

Abstract

Digital technologies and the popularization of e-commerce, social media and metaverse platforms are transforming the fashion industry. Sales through these platforms were pushed up during the COVID-19 pandemic by their intrinsic characteristic of social distancing. This has created a need to effectively communicate with customers and address their needs, preferences, and expectations. Fashion customers are keen to adopting new technologies and digital platforms as they offer a more personalized and meaningful online shopping experience. To improve customers’ experience, many online businesses have implemented recommendations through an interactive interface (e.g., Dialog System (DS)), as a solution. Recommendations in an online fashion retail platform face the problem of being highly dependent on time-varying customers’ preferences and product availability, often leading to an information overload problem. To address this problem, fashion Recommendation Systems (RSs) have benefited from applications of Artificial Intelligence’s techniques, matching customer’s needs and preferences. The DS allows users to interact with the RS and resolve product queries. However, the complexity of human language poses a significant challenge to the effectiveness and acceptance of DSs, particularly in task-oriented (e.g., Marketing & Sales) and context-limited scenarios (e.g., fashion). For instance, a sophisticated but poorly performing DS (e.g., a chatbot) may be worse than a much simpler solution (e.g., a Graphical User Interface (GUI)). As such, designing an efficient and reliable DS is critical to delivering satisfactory user experiences. To address this challenge, this work aims to evaluate a chatbot that serves as an interface for a RS that assists users in finding clothing. To evaluate the chatbot’s performance, usability, hedonic and pragmatic values, potential users in Brazil and the UK assessed their overall satisfaction with the chatbot’s effectiveness in providing personalized recommendations as compared to a simpler GUI. This evaluation contributes to the broader effort to improve and personalize the online fashion shopping experience, particularly by contrasting and comparing the perceptions of consumers from both Brazil and the UK (two of the top five chatbot user countries worldwide) towards chatbots and recommendation systems.

This record has no associated files available for download.

Contributors

Author: Vanissa Wanick

Download statistics