This paper is a review of existing work on adaptive hypermedia. The paper is centered around a set of identified methods and techniques of AH. It introduces several dimensions of classification of AH systems, methods and techniques and describes the most important of them

hypertext in early 1990, it now attracts many researchers from different communities such as hypertext, user modeling, machine learning, natural language generation, information retrieval, intelligent tutoring systems, cognitive science, and Web-based education. model, an adaptable system requires the user to specify exactly how the system should be different, for example, tailoring the sports section to provide information about a favorite team [9]. In different kinds of adaptive systems, adaptation effects could be realized in a variety of ways. Adaptive hypermedia and Web systems are essentially collections of connected information items that allow users to navigate from one item to another and search for relevant items. The adaptation effect in this reasonably rigid context is limited to three major adaptation technologies---adaptive content selection, adaptive navigation support, and adaptive presentation. When the user searches for relevant information, the system can ada

Abstract. Empirical evaluations are needed to determine which users are helped or hindered by user-adapted interaction in user modeling systems. A review of past UMUAI articles reveals insuf¢cient empirical evaluations, but an encouraging upward trend. Rules of thumb for experimental design, useful tests for covariates, and common threats to experimental validity are presented. Reporting standards including effect size and power are proposed. Key words: empirical evaluation, experimental design, covariant variables, e¡ect size, treatment magnitude, power, sensitivity. 1. What Is Empirical Evaluation? Empirical evaluation refers to the appraisal of a theory by observation in experiments. The key to good empirical evaluation is the proper design and execution of the experiments so that the particular factors to be tested can be easily separated from other confounding factors. For example, one may want to test whether a software system with a user model works better than the same system without a user model, test the effect of different levels of user modeling or different user model parameter settings, or test different user interfaces. These factors, which

User modeling has made considerable progress during its existence now of more than a decade. In this paper, a survey of recent developments will be presented, which concentrates on the modeling of a user's knowledge, plans, and preferences in a domain, on the exploitation of new sources of information about the user, on issues of representation, inference and revision, on user modeling shell systems and servers, and on the verification of the practical utility of user models. Research trends and research deficiencies in these areas will be outlined, and potential risks described. 1. Introduction User modeling has made considerable progress during its existence now of more than a decade. Particularly in the last few years, the need for software systems to automatically adapt to their current users has been recognized in many application areas. Consequently, research on user modeling (which originated in the field of natural-language dialog systems) has spread into many disciplines whi...

This paper is devoted to evaluation of adaptive navigation support in educational context. We present an educational hypermedia system ISIS-Tutor that applies several ANS technologies -- adaptive annotation, adaptive hiding, and direct guidance -- and describe a study, which evaluates the first two technologies. The results show that adaptive navigation support is helpful and can reduce user navigation efforts

This paper describes the automatic adaptation of hypertext to the user's presumed domain knowledge in the KN-AHS system, and the support that the user modeling shell system BGP-MS can provide for this adaptation. First, basic hypertext concepts will be introduced and reasons given for why hypertext should adapt to the current user (especially to his/her state of knowledge). A brief overview of those representation and inference components of BGP-MS that are used by KN-AHS will then be provided, followed by a description of its adaptive user interface. The interaction between the adaptive hypertext system and the user modeling system will be investigated in detail based on a possible dialog with a user. Finally, the inter-process communication between KN-AHS and BGP-MS will be described and related work discussed. The aim of this work was to demonstrate the feasibility of user modeling with BGP-MS in a "normal" hardware and software environment that is frequently found in the workplace.

We have evaluated an adaptive hypermedia system, PUSH, and compared it to a non-adaptive variant of the same system. Based on an inferred information seeking task, PUSH chooses what to show and what to hide in a page using a stretchtext technique, thus attempting to avoid information overload. We studied how successful the subjects were in retrieving the most relevant information, and found that the subjects’ solutions were influenced by the choice made by the adaptive system. We also studied how much the adaptivity reduced the amount of actions needed, and found that subjects made substantially fewer actions in the adaptive case. A third measurement was the subjects subjective preferences for the adaptive or the non-adaptive system, were we found that the subjects clearly preferred the adaptive system. It seems as if it requires less decisions on behalf of the subject, thereby reducing their cognitive load.

Utilising adaptive interface techniques in the design of systems introduces certain risks. An adaptive interface is not static, but will actively adapt to the perceived needs of the user. Unless carefully designed, these changes may lead to an unpredictable, obscure and uncontrollable interface. Therefore the design of adaptive interfaces must ensure that users can inspect the adaptivity mechanisms, and control their results. One way to do this is to rely on the user's understanding of the application and the domain, and relate the adaptivity mechanisms to domainspecific concepts. We present an example of an adaptive hypertext help system POP, which is being built according to these principles, and discuss the design considerations and empirical findings that lead to this design.

Intelligent user interfaces have been proposed as a means to overcome some of the problems that directmanipulation interfaces cannot handle, such as: information overflow problems; providing help on how to use complex systems; or real-time cognitive overload problems. Intelligent user interfaces are also being proposed as a means to make systems individualised or personalised, thereby increasing the systems flexibility and appeal.

This paper introduces the special issue of Knowledge-Based Systems on HumanComputer Collaboration (HCC). It derives a set of fundamental issues from a definition of collaboration, introduces two major approaches to HCC, and surveys each approach, showing how it formulates and addresses the issues. It concludes by proposing some themes that should characterize a unified approach to human-computer collaboration. 1 Introduction Collaboration is a process in which two or more agents work together to achieve shared goals. Thirty researchers came together in Raleigh, North Carolina in October of 1993 for a AAAI Fall Symposium dedicated to this topic. The goal of the symposium was to achieve a better understanding of Human-Computer Collaboration (HCC), collaboration involving at least one human and one computational agent. In particular, the symposium sought to explore the fundamental nature of collaborative problem solving, understand the constraints brought to bear by the differing charac...