Abstract
Context is any information/knowledge about an application and user that can be used by an e-commerce system to provide efficient services to the users of the system. In this article, we propose to extend usage of context as compared to previously designed context-aware e-commerce systems. While in previous work, context was mainly considered for mobile e-commerce systems, we propose to build and use context for e-commerce systems in general. The context is employed to tailor an e-commerce application to the preferences and needs of users and provide insights into purchasing activities of users and particular e-commerce stores by means of using Data Mining techniques. This article proposes a model of context that includes micro-, macro- and domain contexts that constitute knowledge about the application and its user on different levels of granularity. The article also proposes a technique for extracting groups in social networks. This knowledge is part of macro-context in the proposed model of context. Moreover, the article discusses some of the challenges of incorporating context with e-commerce systems, emphasizing on the privacy issue, with an ultimate goal of developing intelligent e-commerce systems.
Top2. Background
The research on context-aware e-commerce systems mostly concentrates on mobile-commerce (m-commerce) (Tarasevich (2003), Vassilakis et al. (2007), Thawani et al. (2007), Jin & Miyazawa (2002)). Three broad categories of context are considered in the model of context for m-commerce proposed by Tarasevich (2003), namely environment, participants and activities. The “Environment” component of the model considers the physical properties of objects in the physical environment such as location, brightness, and noise level, etc. The “Participants” category considers properties of the user(s) and other participants. These include the user’s location as well as the user’s personal properties (such as gender, age, education). The “Activities” category includes the tasks and goals that the participants have, it also includes events in the environment (e.g., weather). The model as well considers the possible interactions between different categories of the context model. Time is also incorporated into the model. This enables building context history and predicting the future context.
Vassilakis et al. (2007) discuss the issues, challenges and research directions for mobile and context-aware e-commerce. The context taken into account by the applications can involve location, time of access, the devices used to access an m-commerce application, the communication network, the nature of transaction carried out etc. The challenges that are introduced by the mobile and context-aware e-commerce systems are dictated by the limited communication bandwidth, limited computational power, small screen size of mobile devices (such as PDAs and cell phones). An important aspect of the applications is the user interface issue.
Key Terms in this Chapter
Data Mining (Knowledge Discovery): A process of discovering and extracting patterns in data. It consists of the phases of pre-processing, reporting, exploratory analysis, visualization and modeling.
Point-Wise Mutual Information: A measure of statistical dependence of two entities (e.g., customers of an e-commerce store).
Context: Any information that is relevant to the interaction between a user and computer system.
Social Group: A subset of a social network, which is grouped based on common interests and preferences of nodes.
Context-Awareness: Awareness of a computer system of conditions and changes in the environment, including a user and the application itself.
Social Network: A social structure consisting of nodes representing individuals/organizations and links representing their interactions.
Privacy in E-Commerce Domain: The quality of protecting private information by an e-commerce store from unsanctioned intrusion.
E-Commerce: A division of trade, consisting of buying and selling products and services over an electronic system such as Internet.