Abstract
A major theme of Information Science and Technology research is the study of personalization. The key issue of personalization is the problem of understanding human behaviour and its simulation by machines, in a sense that machines can treat users as individuals with respect to their distinct personalities, preferences, goals and so forth. The general fields of research in personalization are user modeling and adaptive systems, which can be traced back to the late 70s, with the use of models of agents by Perrault, Allen, and Cohen (1978) and the introduction of stereotypes by Rich (1979). With the wide progress in hardware and telecommunications technologies that has led to a vast increase in the services, volume and multimodality (text and multimedia) of content, in the last decade, the need for personalization systems is critical, in order to enable both consumers to manage the volume and complexity of available information and vendors to be competitive in the market.
TopBackground
Personalization techniques enable IS to adapt their structure and content to match the needs and preferences of users based on a user model, which is stored, inferred, or updated dynamically. A simplified form of a user modeling system including personalization mechanisms is represented in Figure 1.
Figure 1. User modeling and personalization mechanisms
The user modeling server acquires and maintains the user’s data through a user profile editor (explicitly) and through different user modeling techniques (implicitly). Among the most used techniques for implicitly constructing user models, acquiring user data, and deriving new facts are: logic-based techniques, stereotype-based reasoning, machine learning techniques, and reasoning with uncertainty (using either Bayesian networks or fuzzy logic techniques). User modeling techniques for personalization mechanisms are extensively overviewed in Razmerita (2003).
The following definition is proposed for personalization of IS: “Personalization of Information Systems is the process that enables interface customization, adaptation of the functionality, structure, content or/and presentation and modality in order to increase its relevance for its individual users.” ISs can include customization and/or adaptive personalization features.
- •
Customization is usually initiated by the user. The user decides to select or exclude certain options from the interface. It is usually associated with interface customization. Many of the actual IS include customization features based on the user’s preferences.
- •
Adaptive personalization. These features are triggered by the system, based on the user’s interaction with the system, or based on the user’s data available in the system. User’s data are usually addressed as user profiles or user models. User models can be created by the users, who enter their data explicitly, or they can be inferred by the system. In the later case, the system tracks the user’s activity with the system and infers characteristics of the user interacting with the system. These characteristics (e.g., domains of interest, goal) are further used for providing personalized interaction.
Key Terms in this Chapter
Personalization: Delivery of content according to the individual user’s needs, characteristics and preferences.
User Profile: A machine-processable description of the user model.
Collaborative Filtering: The method of making automatic predictions (filtering) about the interests of a user by collecting information from other similar users.
Content-Based Filtering: The method of making recommendations to a user by matching user profile entries to content attributes.
User Modeling: The process of creating a set of system assumptions about all aspects of the user, which are relevant to the adaptation of the current user interactions.
Acquisition and Adaptation of User Profiles: The automatic creation and adaptation of a user profile by monitoring the user interaction with the system and employing efficient machine learning algorithms.
Machine Learning: The method for processing a training input and offering support for decision based on this input.