Dr. Chee-Kit Looi from the National Institute of Education (Singapore) will share insights into comprehensive initiatives in Singapore’s education system, which involve partnerships between researchers and class room practice.
Dr. Stacy Marsella from the Institute of Creative Technologies (University of Southern California) will speak about the role of emotion and emotion modeling in systems with virtual characters.
Dr. Alexander Renkl from the University of Freiburg (Germany) will suggest a way of reconciling theoretical views on learning held by proponents of socio-constructivist approaches and cognitively oriented approaches and discuss implications for the design of ITS.
Dr. Steven Ritter from Carnegie Learning, Inc. (Pittsburgh, USA) will speak about the third wave of ITS, which takes advantage of the large user base of real-world ITS for purposes of data mining and end-user authoring.
Emotion and its expression play a powerful role in shaping human behavior. As research has revealed the details of emotion’s role, researchers and developers increasingly have sought to exploit these details in a range of applications. Work in human-computer interaction has sought to infer and influence a user’s emotional state as a way to improve the interaction. Tutoring systems, health interventions and training applications have sought to regulate or induce specific, often quite different, emotional states in learners in order to improve learning outcomes. A related trend in HCI work is the use of emotions and emotional displays in virtual characters that interact with users in order to motivate, engender empathy, induce trust or simply arouse.
Common to many of these applications is the need for computational models of the causes and consequences of emotions. To the extent that emotion’s impact on behavior can be modeled correctly in artificial systems, it can facilitate interactions between computer systems and human users. In this talk, I will give an overview of some of the applications that seek to infer and influence a user’s emotions. I will then go into detail on how emotions can be modeled computationally, including the theoretical basis of the models, how we validate models against human data and how human data are also used to inform the animation of virtual characters.
On Sensible and Less Sensible Conceptions of “Active” and Their Instructional Consequences
Usually ITSs or, more generally, technology-enhanced learning environments are designed to afford active learning in order to optimize meaningful knowledge construction. However, researchers in learning and instruction hold different conceptions of “active learning.” Most socio-constructivist approaches have adopted an active responding stance. They regard visible, open learning activities such as solving complex problems, hands-on activities, or argument with peers as necessary for effective learning. This view, however, is challenged by empirical evidence and has theoretical problems. If we assume that learning takes place in the individual learner’s mind, then what the mind does, and not overt behavior, is central. Accordingly, the active processing stance—the typical stance of most cognitively oriented educational psychologists—regards effective learning as knowledge construction resulting from actively processing to-be-learned content. Although active processing might be necessary for knowledge construction, it can become unfocused. In hypermedia environments, for example, learners may focus on peripheral information, which may delay or even prevent the acquisition of important content. Against this background, I have recently proposed a modification of the active processing stance. The focused processing stance claims that it is crucial that the learners’ active processing is related not only to the learning content but to the central concepts and principles to be learned (e.g., mathematical theorems, physics laws).
The focused processing stance is of special relevance to technology-enhanced learning environments. Many features of these environments that are meant as supportive might actually induce learning-irrelevant additional demands to the learners (e.g., decisions when to use different help facilities), or these features might be sub-optimally used (e.g., overuse of help). Hence, these “supportive” features can distract from the central concepts and principles to be learned. In this talk I will present instructional procedures and findings from three lines of research that are relevant in helping learners focus on central concepts and principles: (a) Replacing problem-solving demands by worked solutions in the beginning of the learning
process in order to reduce unproductive problem-solving attempts; (b) informing the learners of the intended function of a learning environment’s “supportive” features in order to optimize their use; (c) prompting by specifically-designed questions in order to focus the learners’ attention on the central principles of the learning domain. The findings confirm that it is crucial not only to induce active learner involvement but also to support focused processing in order to optimize learning outcomes.
Intelligent tutoring systems work falls into three waves. The first wave involves basic research on technical implementation, including authoring systems and tutoring architectures. Second wave work takes this technological development beyond the laboratory. This work involves deep analysis of domain knowledge and empirical validation of systems. The emerging “third wave” takes advantage of widespread use of systems to refine and improve their effectiveness. Work in this area includes data mining and end-user authoring.
Although many types of systems have followed this evolution, intelligent tutoring systems are uniquely positioned among educational software to take advantage of the third wave. The architecture and authoring work from the first wave and the ability to incorporate domain knowledge and test pedagogical approaches in the second wave
make us well positioned to ride this third wave. In this talk, I will describe Carnegie Learning’s experience in riding these waves. We have taken intelligent tutoring systems for mathematics originally developed at Carnegie Mellon to scale with over 500,000 users per year, and are now riding the third wave to leverage this user base and improve the effectiveness and utility of our systems.
If computers are to interact naturally with humans, they must express social competencies and recognize human emotion. This talk describes the role of technology in responding to both affect and cognition and examines research to identify student emotions (frustration, boredom and interest) with around 80% accuracy using hardware sensors and student self-reports. We also discuss “caring” computers that use animated learning companions to talk about the malleability of intelligence and importance of effort and perseverance. Gender differences were noted in the impact of these companions on student affect as were differences for students with learning disabilities. In both cases, students who used companions showed improved math attitudes, increased motivation and reduced frustration and anxiety over the long term. We also describe social tutors that scaffold collaborative problem solving in ill-defined domains. These tutors use deep domain understanding of students’ dialogue to recognize (with over 85% accuracy) students who are engaged in useful learning activities. Finally, we describe tutors that help online participants engaged in situations involving differing opinions, e.g., in online dispute mediation, bargaining, and civic deliberation processes.