H.J.A. op den Akker

Emotional characters for automatic plot creation

The Virtual Storyteller is a multi-agent framework for automatic story generation. In this paper we describe how plots emerge from the actions of semi-autonomous character agents, focusing on the influence of the characters’ emotions on plot development.

An agent-based intelligent tutoring system for nurse education

This report describes the development of a teaching environment that uses agents to support learning. An Intelligent Tutoring System will be described, that guides students during learning. This system is meant for nurse education in the first place, but it is generic in the sense that the core is separated from the exercise modules and user interfaces. This means that the system can also be used for other (non-nursing) exercises. Exercises can be provided to the system in the form of XML data-files. A user interface can be text-based or 2D, but it can also be a 3D virtual reality environment. An application of the teaching environment for nurse training is described.

Affective Feedback in a Tutoring System for Procedural Tasks

We discuss the affective aspects of tutoring dialogues in an ITS -called INES- that helps students to practice nursing tasks using a haptic device and a virtual environment. Special attention is paid to affective control in the tutoring process by means of selecting the appropriate feedback, taking into account elements of the student’s character, the harmfulness of errors made, and the emotional effects of errors and feedback. The tutoring system will adjust both the affective language used and the overall teaching tactics.

Follow-up question handling in the imix and ritel systems: A comparative study

One of the basic topics of question answering (QA) dialogue systems is how follow-up questions should be interpreted by a QA system. In this paper, we shall discuss our experience with the IMIX and Ritel systems, for both of which a follow-up question handling scheme has been developed, and corpora have been collected. These two systems are each others opposites in many respects: IMIX is multimodal, non-factoid, black-box QA, while Ritel is speech, factoid, keyword-based QA. Nevertheless, we will show that they are quite comparable, and that it is fruitful to examine the similarities and differences. We shall look at how the systems are composed, and how real, non-expert, users interact with the systems. We shall also provide comparisons with systems from the literature where possible, and indicate where open issues lie and in what areas existing systems may be improved. We conclude that most systems have a common architecture with a set of common subtasks, in particular detecting follow-up questions and finding referents for them. We characterise these tasks using the typical techniques used for performing them, and data from our corpora. We also identify a special type of follow-up question, the discourse question, which is asked when the user is trying to understand an answer, and propose some basic methods for handling it.

Developing a generic agent-based intelligent tutoring system

We developed a generic teaching environment that uses agents to support learning. An agent platform developed in our research group is used. The system is generic in the sense that the cognition core (domain model, student model and instruction model) is separated from the exercise modules and user interfaces. The architecture allows different user interfaces. An application of the environment for nurse training has been implemented.

Promoting a healthy lifestyle: Towards an improved personalized feedback approach

Technology supported services for achieving a healthy lifestyle have shown their short term effects and are receiving increasing interest from the research community. However, long term adherence to these services is poor. This paper describes research-in-progress regarding the implementation of automated goal-setting and tailored feedback messages into one such technology supported service, which aims to improve the users physical activity pattern. Tailored feedback messages for several personas were set up based on theories from behavioral science and categorized by experts during an expert workshop. Results indicate reasonable agreement on the matching of motivational messages to four personas. Additional expert input is discussed descriptively. Future research will focus on examining the effectiveness of the new version of the service under investigation.

Virtual Coaches for Healthy Lifestyle

Since the introduction of the idea of the software interface agent the question recurs whether these agents should be personified and graphically visualized in the interface. In this chapter we look at the use of virtual humans in the interface of healthy lifestyle coaching systems. Based on theory of persuasive communication we analyse the impact that the use of graphical interface agents may have on user experience and on the efficacy of this type of persuasive systems. We argue that research on the impact of a virtual human interface on the efficacy of these systems requires longitudinal field studies in addition to the controlled short-term user evaluations in the field of human computer interaction (HCI). We introduce Kristina, a mobile personal coaching system that monitors its user’s physical activity and that presents feedback messages to the user. We present results of field trials (N = 60, 7 weeks) in which we compare two interface conditions on a smartphone. In one condition feedback messages are presented by a virtual animated human, in the other condition they are displayed on the screen in text. Results of the field trials show that user motivation, use context and the type of device on which the feedback message is received influence the perception of the presentation format of feedback messages and the effect on compliance to the coaching regime.