Shopping Decisions Made in a Virtual World: Defining a State-Based Model of Collaborative and Conversational User-Recommender Interactions

Abstract

A 3D Virtual World facilitates users' interaction as they feel immersed and engaged in a shared virtual space. This type of interface may be specially useful when consumers employ home electronics for accessing online personalized services. In a previous research we focused on a Collaborative Conversational Recommender framework, where a synchronous and online 3D interface for multiple consumers integrates with a recommender. In this paper we go further and define a state-based model of user-recommender interaction that allows users move from different states of interaction (i.e., individual and collaborative) among users. Then, it is evaluated with users and compared with an individual approach. Our results demonstrate that the collaborative capacities proposed in the framework improves user experience and significantly increases the performance of the recommendation process, i.e users take less time in achieving the desired service.

Evaluating conversational recommender systems

“…Likewise, some measures listed under User Beliefs in the ResQue framework, e.g., Control, would probably fall under Quality of the Conversation and Usability, whereas the Usefulness measure rather relates to Effectiveness of Task and Ziegler (2016). Various terms for accuracy are used in the literature, e.g., match with user preferences (Ricci and Nguyen 2007), perceived accuracy (Contreras et al 2018), or recommendation quality (Grasch et al 2013). The attractiveness of entire item sets was, e.g., considered in a non-CRS work in Willemsen et al (2016).…”

“…The extent to which a CRS in a virtual environment supported collaboration between users was assessed in Contreras et al (2014Contreras et al ( , 2018.…”

“…Today's datasets for learning, e.g., the ReDial dataset, however seem to be too limited to allow for such a learning approach. While the number of recorded dialogues is not small, a closer In user studies, alternative quantitative measures are used, e.g., the "position of the selected item" or the "fraction of users switching their decision later on" (Averjanova et al 2008a;Contreras et al 2018). In user studies, task completion rates, success rates or (virtual) purchases can inform about the adoption of the recommendations or advice by users, e.g., Wang and Benbasat (2013), Mahmood and Ricci (2009), Sun et al (2013), Yu et al (2019b), Tsumita and Takagi (2019).…”

A Survey on Conversational Recommender Systems

“…Finally, a few works exist where users interact with a recommendation system within a virtual, three-dimensional space. In [33,34], for example, the authors describe a virtual shopping environment where users interact with a critiquing-based recommender and can, in addition, collaborate with other users. Supporting group decisions is also the goal of the work presented in [1].…”

“…A product database with more than 600 distinct products was collected from various retailers [46]. A smartphone database consisting of 1721 products with multiple features [34]. Amazon electronics review dataset 5 containing millions of products, user reviews and product meta-data [164].…”