Recently, interactive storytelling systems – systems that allow a user to

Abstract. Self-efficacy is an individual’s belief about her ability to perform well in a given situation. Because selfefficacious students are effective learners, endowing intelligent tutoring systems with the ability to diagnose selfefficacy could lead to improved pedagogy. Self-efficacy is influenced by (and influences) affective state. Thus, physiological data might be used to predict a student’s level of self-efficacy. This article investigates an inductive approach to automatically constructing models of self-efficacy that can be used at runtime to inform pedagogical decisions. It reports on two complementary empirical studies. In the first study, two families of self-efficacy models were induced: a static self-efficacy model, learned solely from pre-test (non-intrusively collected) data, and a dynamic self-efficacy model, learned from both pre-test data as well as runtime physiological data collected with a biofeedback apparatus. In the second empirical study, a similar experimental design was applied to an interactive narrative-centered learning environment. Self-efficacy models were induced from combinations of static and dynamic information including pre-test data, physiological data, and observations of student behavior in the learning environment. The highest performing induced naïve Bayes models correctly classified 85.2 % of instances in the first empirical study and 82.1 % of instances in the second empirical study. The highest performing decision tree models correctly classified 86.9 % of instances in the first study and 87.3 % of instances in the second study.

In recent years, there has been a growing interest in constructing rich interactive entertainment and training experiences. As these experiences have grown in complexity, there has been a corresponding growing need for the development of robust technologies to shape and modify those experiences in reaction to the actions of human participants. One popular mechanism for addressing this need is through the use of a drama manager. A drama manager is a coordinator that tracks narrative progress in the environment and directs the roles and/or responses of objects and agents in order to achieve a specified narrative or training goal. In this paper, we provide a survey of recent advances in drama management technologies for interactive entertainment, and describe a set of desiderata for the qualitative analysis of such systems.

We present a narrative theory-based approach to data mining that generates cohesive stories from a Wikipedia corpus. This approach is based on a data mining-friendly view of narrative derived from narratology, and uses a prototype mining algorithm that implements this view. Our initial test case and focus is that of field-based educational tour narrative generation, for which we have successfully implemented a proof-of-concept system called Minotour. This system operates on a client-server model, in which the server mines a Wikipedia database dump to generate narratives between any two spatial features that have associated Wikipedia articles. The server then delivers those narratives to mobile device clients. 1.

Abstract. Recent years have seen growing interest in narrative-centered learning environments. Leveraging the inherent structure of narrative, narrativecentered learning environments offer significant potential for inquiry-based learning in which students actively participate in engaging story-based problem-solving. A key challenge posed by narrative-centered learning is orchestrating all of the events in the unfolding story to motivate students and promote effective learning. In this paper we present a narrative-centered tutorial planning architecture that integrates narrative planning and pedagogical control. The architecture continually constructs and updates narrative plans to support the hypothesis-generation-testing cycles that form the basis for inquiry-based learning. It is being used to implement a prototype narrative-centered inquirybased learning environment for the domain of microbiology. The planner dynamically balances narrative and pedagogical goals while at the same time satisfying the real-time constraints of highly interactive learning environments. 1

Abstract. Narrative-centered learning environments hold much promise for education and training. Much of the appeal of narrative-centered learning lies in the belief that narrative context provides a meaningful structure integrating pedagogical objectives into a unifying, coherent form that serves as a powerful

Context has been linked in previous reports to student motivation in introductory CS courses. In this report, we consider the role of context in a second course. We present a case study of a CS2 data structures class that uses a media computation context. In this course, students learn data structures and object-oriented programming through a pervasive narrative about how real media professionals use data structures to model the real world and to construct the digital images, sounds, and animations with which the students are familiar in their daily lives. We found that context played a different role in a second course than in a first course. We found evidence that some students had out-grown the desire for a context, and we found evidence that context can help students get engaged with the material that they otherwise do not find interesting. In particular, the narrative aspect of a context may help students in relating the elements of the course and may even help with learning.

Introduction The term "chance" is characterized as information about an event or situation that has significant influence on the decision-making process of a human or artificial agent. Depending on whether this information suggests a desirable or undesirable future development, a chance is perceived as an opportunity or as a risk. Chance discovery can be described as the process of becoming aware of an opportunity or of a risk. After the situation or event is identified as a chance, it can `be taken' (or ignored) and constitute an essential part of the decision-making process (Ohsawa and Nara [1.22]). Chances, or knowledge about chances, do not necessarily have to be `new' in the sense of an opportunity or risk never encountered before. Often, chance knowledge is part of the experience of humans who managed to turn an opportunity into success or were able to avoid some risk. In organizations, this kind of knowledge is known as tacit knowledge, and is typically contrasted with explici

Abstract. In this paper, we are focusing on digital serious games (edugames) and how they can be utilized in teaching in the ethics and citizenship domain. Our aim is to combine narrative techniques with intelligent tutoring techniques in a single model that adopts and based on educational theories and classroom educational strategies. The model has been used to implement an adaptive educational interactive narrative system (AEINS). AEINS is an inquiry based edugame to support teaching ethics. The AEINS version presented in this paper targets students between the age of 8 and 11. The idea is centered around presenting and involving students in different moral dilemmas (called teaching moments) within which the Socratic Method is the used pedagogy in the teaching process. AEINS monitors and analyzes the students actions in order to provide an individualized story-path and an individualized learning process. The student is an active participant in the educational process and is able to interact with the edugame as a first person player. We claim that such interaction can help in developing new or deeper thoughts about different moral situations. Our aim is to contribute to the design of serious games and help raise awareness of ethics and citizenship in children. 1

Social Computing aims to support the tendency of humans to interact with computers as if they were veritable social actors. Technology that reinforces the bias toward social interaction by producing appropriate responses may improve the communication between humans and computational devices. We believe that the most natural way to realize social computing is by using life-like synthetic characters with context aware affective behavior. We will