Kristina Höök

Steps to take before intelligent user interfaces become real

Abstract Intelligent user interfaces have been proposed as a means to overcome some of the problems that direct manipulation 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 system’s flexibility and appeal. Unfortunately, there are a number of problems not yet solved that prevent us from creating good intelligent user interface applications. We do not have efficient methods for developing them. There are demands on better usability principles for them. We need a better understanding of the possible ways the interface can utilise intelligence to improve the interaction. Finally, we need to design better tools that will enable an intelligent system to survive the full life cycle of a system (including updates of the database, system support, etc.). We define these problems further and point out some possible solutions.

Evaluating the utility and usability of an adaptive hypermedia system

We have evaluated an adaptive hypermedia system, named PUSH, and compared it to a non-adaptive variant of the same system. The PUSH system either infers users’ information-seeking tasks from their actions at the interface, or the users can set the task themselves. Based on the information-seeking task, the system chooses what to show and what to hide in a page using a stretchtext1 technique. The purpose is 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. We also discuss the general problem of evaluating adaptive systems.

Towards tangibility in gameplay: building a tangible affective interface for a computer game

In this paper we describe a way of controlling the emotional states of a synthetic character in a game (FantasyA) through a tangible interface named SenToy. SenToy is a doll with sensors in the arms, legs and body, allowing the user to influence the emotions of her character in the game. The user performs gestures and movements with SenToy, which are picked up by the sensors and interpreted according to a scheme found through an initial Wizard of Oz study. Different gestures are used to express each of the following emotions: anger, fear, happiness, surprise, sadness and gloating. Depending upon the expressed emotion, the synthetic character in FantasyA will, in turn, perform different actions. The evaluation of SenToy acting as the interface to the computer game FantasyA has shown that users were able to express most of the desired emotions to influence the synthetic characters, and that overall, players, especially children, really liked the doll as an interface.

Demo: playingfFantasyA with senToy

Game development is an emerging area of development for new types of interaction between computers and humans. New forms of communication are now being explored there, influenced not only by face to face communication but also by recent developments in multi-modal communication and tangible interfaces. This demo will feature a computer game, FantasyA, where users can play the game by interacting with a tangible interface, SenToy (see Figure 1). The main idea is to involve objects and artifacts from real life into ways to interact with systems, and in particular with games. So, SenToy is an interface for users to project some of their emotional gestures through moving the doll in certain ways. This device would establish a link between the users (holding the physical device) and a controlled avatar (embodied by that physical device) of the computer game, FantasyA.