Search

Pedagogical agents have been designed to support the significant challenges that learners face when self-regulating in advanced learning environments. Evidence suggests differences in learners' prior skills and abilities, in conjunction with excessive didactic support, can cause overreliance on these external aids, which in turn prevents deeper learning, and pedagogical agents can provide tailored scaffolding to accommodate learners' individual needs. However, there is less evidence about the impact of abstract scaffolding, such as the sharing of non-verbal metacognitive information via a pedagogical agent's facial expressions, on self-regulated learning. To assess factors in the passing of non-verbal metacognitive information via pedagogical agents in a multimedia learning environment, we used growth modeling with self-reports, eye-tracking, and log-file data collected from fifty (n = 50) undergraduates at a large North American university as they learned about human body systems while using MetaTutor-IVH, a multimedia learning environment with a pedagogical agent. We controlled for participant characteristics (perceived utility of emotions for self- and other-centered positive and negative emotions) and characteristics of the metacognitive monitoring information provided by a pedagogical agent (expression type and expression congruency) to assess factors in non-verbally communicating metacognitive information. Results suggest that learners attend to pedagogical agents less over time, but this rate of change is weaker when an agent is providing an expression that is congruent with the ground truth of the environment. Further, only the perceived information utility of other-centered negative emotions has a significant effect on this duration, suggesting learners are driven to consult pedagogical agents to avoid embarrassment or shame. We discuss design implications of these findings for technology-based learning environments.

Science learning is inherently multimodal, with students utilizing both drawings and writings to explain observations of physical phenomena. As such assessments in science should accommodate the many ways students express their understanding, especially given evidence that understanding is distributed across both drawing and writing. In recent years advanced automated assessment techniques that evaluate expressive student artifacts have emerged. However, these techniques have largely operated individually, each considering only a single mode. We propose a framework for the multimodal automated assessment of students' writing and drawing to leverage the synergies inherent across modalities and create a more complete and accurate picture of a student's knowledge. We introduce a multimodal assessment framework as well as two computational techniques for automatically analyzing student writings and drawings: a convolutional neural network-based model for assessing student writing, and a topology-based model for assessing student drawing. Evaluations with elementary students' writings and drawings collected with a tablet-based digital science notebook demonstrate that (1) each of the framework's two modalities provide an independent and complementary measure of student science learning, and (2) the computational methods are capable of accurately assessing student work from both modalities and offer the potential for integration in technology-rich learning environments for real-time formative assessment.

Over the past decade, there has been growing interest in real-time assessment of student engagement and motivation during interactions with educational software. Detecting symptoms of disengagement, such as off-task behavior, has shown considerable promise for understanding students' motivational characteristics during learning. In this paper, we investigate the affective role of off-task behavior by analyzing data from student interactions with CRYSTAL ISLAND, a narrative-centered learning environment for middle school microbiology. We observe that off-task behavior is associated with reduced student learning, but preliminary analyses of students' affective transitions suggest that off-task behavior may also serve a productive role for some students coping with negative affective states such as frustration. Empirical findings imply that some students may use off-task behavior as a strategy for self-regulating negative emotional states during learning. Based on these observations, we introduce a supervised machine learning procedure for detecting whether students' off-task behaviors are cases of emotion self-regulation. The method proceeds in three stages. During the first stage, a dynamic Bayesian network (DBN) is trained to model the valence of students' emotion self-reports using collected data from interactions with the learning environment. In the second stage, a novel simulation process uses the DBN to generate "alternate futures" by modeling students' affective trajectories as if they had engaged in fewer off-task behaviors than they did during their actual learning interactions. The alternate futures are compared to students' actual traces to produce labels denoting whether students' off-task behaviors are cases of emotion self-regulation. In the final stage, the generated emotion self-regulation labels are predicted using off-the-shelf classifiers and features that can be computed in run-time settings. Results suggest that this approach shows promise for identifying cases of off-task behavior that are emotion self-regulation. Analyses of the first two phases suggest that trained DBN models are capable of accurately modeling relationships between students' off-task behaviors and self-reported emotional valence in CRYSTAL ISLAND. Additionally, the proposed simulation process produces emotion self-regulation labels with high levels of reliability. Preliminary analyses indicate that support vector machines, bagged trees, and random forests show promise for predicting the generated emotion self-regulation labels, but room for improvement remains. The findings underscore the methodological potential of considering alternate futures when modeling students' emotion self-regulation processes in narrative-centered learning environments.

Tutoring systems that are sensitive to affect show considerable promise for enhancing student learning experiences. Creating successful affective responses requires considerable effort both to detect student affect and to design appropriate responses to affect. Recent work has suggested that affect detection is more effective when both physical sensors and interaction logs are used, and that context-sensitive design of affective feedback is necessary to enhance engagement and improve learning. In this paper, we provide a comprehensive report on a multi-part study that integrates detection, validation, and intervention into a unified approach. This paper examines the creation of both sensor-based and interaction-based detectors of student affect, producing successful detectors of student affect. In addition, it reports results from an investigation of motivational feedback messages designed to address student frustration, and investigates whether linking these interventions to detectors improves outcomes. Our results are mixed, finding that self-efficacy enhancing interventions based on interaction-based affect detectors enhance outcomes in one of two experiments investigating affective interventions. This work is conducted in the context of the GIFT framework for intelligent tutoring, and the TC3Sim game-based simulation that provides training for first responder skills.

In recent years, significant advances have been made in intelligent tutoring systems, and these advances hold great promise for adaptively supporting computer science (CS) learning. In particular, tutorial dialogue systems that engage students in natural language dialogue can create rich, adaptive interactions. A promising approach to increasing the effectiveness of these systems is to adapt not only to problem-solving performance, but also to a student's characteristics. Self-efficacy refers to a student's view of her ability to complete learning objectives and to achieve goals; this characteristic may be particularly influential during tutorial dialogue for computer science education. This article examines a corpus of effective human tutoring for computer science to discover the extent to which considering self-efficacy as measured within a pre-survey, coupled with dialogue and task events during tutoring, improves models that predict the student's self-reported frustration and learning gains after tutoring. The analysis reveals that students with high and low self-efficacy benefit differently from tutorial dialogue. Student control, social dialogue, and tutor moves to increase efficiency, may be particularly helpful for high self-efficacy students, while for low self-efficacy students, guided experimentation may foster greater learning while at the same time potentially increasing frustration. It is hoped that this line of research will enable tutoring systems for computer science to tailor their tutorial interactions more effectively.

Johnson et al. ("International Journal of Artificial Intelligence in Education," 11, 47-78, 2000) introduced and surveyed a new paradigm for interactive learning environments: animated pedagogical agents. The article argued for combining animated interface agent technologies with intelligent learning environments, yielding intelligent systems that can interact with learners in natural, human-like ways to achieve better learning outcomes. We outlined a variety of possible uses for pedagogical agents. But we offered only preliminary evidence that they improve learning, leaving that to future research and development. Twenty years have elapsed since work began on animated pedagogical agents. This article re-examines the concepts and predictions in the 2000 article in the context of the current state of the field. Some of the ideas in the paper have become well established and widely adopted, especially in game-based learning environments. Others are only now being realized, thanks to advances in immersive interfaces and robotics that enable rich face-to-face interaction between learners and agents. Research has confirmed that pedagogical agents can be beneficial, but not equally for all learning problems, applications, and learner populations. Although there is a growing body of research findings about pedagogical agents, many questions remain and much work remains to be done.

Affect has been the subject of increasing attention in cognitive accounts of learning. Many intelligent tutoring systems now seek to adapt pedagogy to student affective and motivational processes in an effort to increase the effectiveness of tutorial interaction and improve learning outcomes. To this end, recent work has begun to investigate the emotions experienced during learning in a variety of environments. In this paper we extend this line of research by investigating the affective transitions that occur throughout narrative-centered learning experiences. Further analysis differentiates the likelihood of affective transitions stemming from pedagogical agent empathetic responses to student affect. (Contains 2 tables and 10 figures.)

The Generalized Intelligent Framework for Tutoring (GIFT) is a research prototype with three general goals associated with its functions and components: 1) lower the skills and time required to author Intelligent Tutoring Systems (ITSs) in a variety of task domains; 2) provide effective adaptive instruction tailored to the needs of each individual learner or team of learners; and 3) provide tools and methods to evaluate the effectiveness of ITSs and support research to continuously improve instructional best practices. This special issue focuses primarily on the third goal, GIFT as a research testbed. A discussion thread covers each article within this special issue and discusses its actual and potential impact on GIFT as a research tool for AIED. Our primary motivation was to introduce the AIED community to GIFT not just as a research tool, but as an extension of familiar challenges taken on previously by AIED scientists and practitioners. This preface provides a high level overview of the GIFT functions (authoring, instructional delivery and management, and experimentation) and presents its primary design principles. To learn more about GIFT, freely access the software, documentation, and associated technical papers visit www.GIFTtutoring.org. [ABSTRACT FROM AUTHOR]

Intelligent game-based learning environments integrate commercial game technologies with Al methods from intelligent tutoring systems and intelligent narrative technologies. This article introduces the Crystal Island intelligent game-based learning environment, which has been under development in the authors' laboratory for the past seven years. After presenting Crystal Island, the principal technical problems of intelligent game-based learning environments are discussed: narrative-centered tutorial planning, student affect recognition, student knowledge modeling, and student goal recognition. Solutions to these problems are illustrated with research conducted with the Crystal Island learning environment. [ABSTRACT FROM AUTHOR]

In recent years, there have been significant advances in tutoring systems that engage students in rich natural language dialogue. With the goal of further understanding what makes tutorial dialogue successful, this article presents a corpus-based approach to modelling the differential effectiveness of tutorial dialogue strategies with respect to learning. We present results of a study in which task-oriented, textual tutorial dialogue was collected from remote one-on-one human tutoring sessions. This article extends a previous study which found that certain dialogue acts were correlated with learning and student characteristics in the corpus. The predictive models presented here demonstrate important differences between the dialogue sequences that were correlated with learning for different groups of students. The models demonstrate that tutor directives, a type of bottom-out hint, were negatively associated with learning for students with low incoming knowledge or low self-efficacy. The findings signal the importance of tutorial dialogue that adapts to learner characteristics. [ABSTRACT FROM AUTHOR]

Identifying effective tutorial dialogue strategies is a key issue for intelligent tutoring systems research. Human-human tutoring offers a valuable model for identifying effective tutorial strategies, but extracting them is a challenge because of the richness of human dialogue. This article addresses that challenge through a machine learning approach that 1) learns tutorial modes from a corpus of human tutoring, and 2) identifies the statistical relationships between student outcomes and the learned modes. The modeling approach utilizes hidden Markov models (HMMs) to capture the unobservable stochastic structure that is thought to influence the observations, in this case dialogue acts and task actions, that are generated by task-oriented tutorial dialogue. We refer to this unobservable layer as the hidden dialogue state, and interpret it as representing the tutor and students' collaborative intentions. We have applied HMMs to a corpus of annotated task-oriented tutorial dialogue to learn one model for each of two effective human tutors. Significant correlations emerged between the automatically extracted tutoring modes and student learning outcomes. Broadly, the results suggest that HMMs can learn meaningful hidden tutorial dialogue structure. More specifically, the findings point to specific mechanisms within task-oriented tutorial dialogue that are associated with increased student learning. This work has direct applications in authoring data-driven tutorial dialogue system behavior and in investigating the effectiveness of human tutoring. [ABSTRACT FROM AUTHOR]

The article analyzes the influence of Artificial Intelligence (AI) in education. According to the author, Kurt VanLehn has an excellent viewpoint on the evolution of intelligent tutoring systems and his framework marks the arrival of AI in Education as a mature field apart from serving recommendations as the foundation for standardization efforts. The framework has an unusual design that effectively informs and serves the needs of the AI in the Education community.

Mixed-initiative problem solving lies at the heart of knowledge- based learning environments. While learners are actively engaged in problem-solving activities, learning environments should monitor their progress and provide them with feedback in a manner that contributes to achieving the twin goals of learning effectiveness and learning efficiency. Mixed-initiative interactions are particularly critical for constructivist learning environments in which learners participate in active problem solving. We have recently begun to see the emergence of believable agents with lifelike qualities. Featured prominently in constructivist learning environments, lifelike pedagogical agents could couple key feedback functionalities with a strong visual presence by observing learners' progress and providing them with visually contextualized advice during mixed-initiative problem solving. For the past three years, we have been engaged in a large-scale research program on lifelike pedagogical agents and their role in constructivist learning environments. In the resulting computational framework, lifelike pedagogical agents are specified by (1) a behavior space containing animated and vocal behaviors, (2) a design-centered context model that maintains constructivist problem representations, multimodal advisory contexts, and evolving problem-solving tasks, and (3) a behavior sequencing engine that in realtime dynamically selects and assembles agents' actions to create pedagogically effective, lifelike behaviors. To empirically investigate this framework, it has been instantiated in a full-scale implementation of a lifelike pedagogical agent for Design-A-Plant, a learning environment developed for the domain of botanical anatomy and physiology for middle school students. Experience with focus group studies conducted with middle school students interacting with the implemented agent suggests that lifelike pedagogical agents hold much promise for mixed-initiative learning. [ABSTRACT FROM AUTHOR]

Affective reasoning holds significant potential for intelligent tutoring systems. Incorporating affective reasoning into pedagogical decision-making capabilities could enable learning environments to create customised experiences that are dynamically tailored to individual students' ever-changing levels of engagement, interest, motivation and self-efficacy. Because physiological responses are directly triggered by changes in affect, biofeedback data such as heart rate and galvanic skin response can be used to infer affective changes in conjunction with the situational context. This article explores an approach to inducing affect models for a learning environment. The inductive approach is examined for the task of modelling students' self-efficacy and empathy for companion agents. Together, these studies on affect in a narrative learning environment suggest that it is possible to build models of affective constructs from observations of the situational context and students' physiological response. [ABSTRACT FROM AUTHOR]