David Jingjun Xu

Combining empirical experimentation and modeling techniques: A design research approach for personalized mobile advertising applications

We propose a design research approach combining behaviour and engineering techniques to better support user modeling in personalized mobile advertising applications. User modeling is a practical means of enabling personalization; one important method to construct user models is that of Bayesian networks. To identify the Bayesian network structure variables and the prior probabilities, empirical experimentation is adopted and context, content, and user preferences are the salient variables. User data collected from the survey are used to set the prior probabilities for the Bayesian network. Experimental evaluation of the system shows it is effective in improving user attitude toward mobile advertising.

A Bayesian Network-Based Framework for Personalization in Mobile Commerce Applications

Providing personalized services for mobile commerce (m-commerce) can improve user satisfaction and merchant profits, which are important to the success of m-commerce. This paper proposes a Bayesian network (BN)-based framework for personalization in m-commerce applications. The framework helps to identify the target mobile users and to deliver relevant information to them at the right time and in the right way. Under the framework, a personalization model is generated using a new method and the model is implemented in an m-commerce application for the food industry. The new method is based on function dependencies of a relational database and rough set operations. The framework can be applied to other industries such as movies, CDs, books, hotel booking, flight booking, and all manner of shopping settings.

The outcomes and the mediating role of the functional triad: The users' perspective

B.J. Foggs Functional Triad shows the manner in which computing technologies can persuade people by playing 3 different functional roles, namely, as tools, media, or social actors. However, the effects of user perceptions of these 3 functional roles are largely unknown. We advance Foggs framework by developing a conceptual model to explain how a feature of a computing technology (ie, the trade‐off transparency feature of a recommendation agent [RA], which interactively demonstrates the trade‐offs among product attribute values) can result in certain outcomes by shaping the beliefs of individuals regarding the 3 functional roles. We examine the effects of the perceived Functional Triad on the following 3 outcomes: (1) persuading users to use an RA (intention to use), (2) persuading users to follow the advice of the RA (recommendation adherence), and (3) persuading users to recommend the RA to others (recommendation to friends). We conducted a laboratory experiment to manipulate 4 levels of trade‐off transparency, thereby creating an adequate amount of variations for the perceived Functional Triad. A total of 160 participants were recruited from a large university in North America. Although designers could control the technology design aspects, these designs may not accomplish the intended effects on users, who have their own perceptions. This study contributes to existing literature by simultaneously evaluating the 3 different outcomes of the Functional Triad from the perspective of users.

A Two-Stage Model of Generating Product Advice: Proposing and Testing the Complementarity Principle

Abstract Most extant research into product recommendations focuses on how advice from recommendation agents (RAs), consumers, or experts facilitates an initial (or single-stage) screening of available products and provides relevant product recommendations. The literature has largely overlooked the possibility and effects of the second stage of product advice using a recommendation improvement (RI) functionality, during which users can refine and improve the accuracy of the first-stage product recommendations. Thus, our understanding of how users make product choices is incomplete. To rectify this, we propose a two-stage model of generating product advice, and we use it to test what we propose as the complementarity principle. This principle posits that the first-stage recommendations (personalized or nonpersonalized) influence the impact of different types of second-stage RI functionality, which augment the first stage by facilitating either alternative-based or attribute-based processing. Results show that the complementary synergies between the two stages result in higher perceived decision quality, but at the expense of higher perceived decision effort. We contribute to the literature by helping researchers better understand users’ adoption of the second-stage RI functionality in conjunction with first-stage recommendations. In addition, e-commerce designers are advised to provide different and complementary types of recommendation sources and RI functionalities to facilitate online consumers’ decision making.