We are witnessing the development of new communication technologies (e.g., DTV networks [digital TV], 3G [thirdgeneration] telephony, and DSL [digital subscriber line]) and a rapid growth in the amount of information available. In this scenario, users were supposed to benefit extensively from services delivering news, entertainment, education, commercial functionalities, and so forth. However, the current situation may be better referred to as information overload; as it frequently happens that users are faced with an overwhelming amount of information. A similar situation was noticeable in the 1990s with the exponential growth of the Internet, which made users feel disoriented among the myriad of contents available through their PCs. This gave birth to search engines (e.g., Google and Yahoo) that would retrieve relevant Web pages in response to user-entered queries. These tools proved effective, with millions of people using them to find pieces of information and services. However, the advent of new devices (DTV receivers, mobile phones, media players, etc.) introduces consumption and usage habits that render the search-engine paradigm insufficient. It is no longer realistic to think that users will bother to visit a site, enter queries describing what they want, and select particular contents from among those in a list. The reasons may relate to users adopting a predominantly passive role (e.g., while driving or watching TV), the absence of bidirectional communication (as in broadcasting environments), or users feeling uneasy with the interfaces provided. To tackle these issues, a large body of research is being devoted nowadays to the design and provision of personalized information services, with a new paradigm of recommender systems proactively selecting the contents that match the interests and needs of each individual at any time. This article describes the evolution of these services, followed by an overview of the functionalities available in diverse areas of application and a discussion of open problems. Background The development of personalized information
The development of personalized information services brings together diverse areas of technology, plus a significant body of legislation. The following subsections group these aspects into five major topics.
To identify the most suitable contents for a user, it is necessary to handle profiles that capture the user’s preferences and needs. Such profiles can be represented in many different ways: consumption histories, ontologies, neural networks, decision trees, and so on (Conati, McCoy, & Paliouras, 2007). Besides these, there exist many de jure or de facto application-dependent standards to manage data: learner information packaging (LIP) to track educational activities, TV-Anytime for TV programs, Integrating the Healthcare Enterprise (IHE) for health records, and so forth.
The initialization of the user profiles can be done manually, with the user entering a description of his or her interests, or automatically, with the program retrieving information from his or her interactions with other systems (e.g., commonly, from Web navigation histories). Whichever the approach, a recommender system must implement mechanisms to capture new data (relevance feedback) and discard obsolete information (gradual forgetting). For relevance feedback, some systems use explicit mechanisms that require the user to rate contents as interesting or not interesting; others provide implicit mechanisms that infer information from ongoing interactions (Montaner, López, & de la Rosa, 2003). In gradual forgetting, the common approach is to measure the obsolescence of data in the profiles as a function of time.
Key Terms in this Chapter
Collaborative Filtering: Collaborative filtering includes techniques to estimate the relevance of a given service or piece of content for a target user, considering the ratings given by other users with similar profiles to the same resource or to similar ones.
Recommender systems: These are software systems that proactively look for services and pieces of content that may be relevant for a target user or group of users, matching user profiles, contextual information, and metadata describing the resources available.
Context Awareness: It is the ability of an information system to adapt to a user’s changing attention, location, and physical environment.
Information Overload: It is a situation in which it is hard for a user to stay informed or make decisions about a given topic due to being exposed to an excessive amount of information.
Personalized Information Service: It is a system that delivers information tailored to the interests, preferences, needs, and context of a user or a group of users.
User Profiles: User profiles are data structures containing information that may be used to characterize the interests, preferences, and needs of a user.
Content-Based Filtering: This includes techniques to estimate the relevance of a given service or piece of content for a target user, considering that user’s previous ratings for resources consumed in the past.