Showing papers on "Intelligent tutoring system published in 2007"

Automatic prediction of frustration

Abstract: Predicting when a person might be frustrated can provide an intelligent system with important information about when to initiate interaction. For example, an automated Learning Companion or Intelligent Tutoring System might use this information to intervene, providing support to the learner who is likely to otherwise quit, while leaving engaged learners free to discover things without interruption. This paper presents the first automated method that assesses, using multiple channels of affect-related information, whether a learner is about to click on a button saying ''I'm frustrated.'' The new method was tested on data gathered from 24 participants using an automated Learning Companion. Their indication of frustration was automatically predicted from the collected data with 79% accuracy (chance=58%). The new assessment method is based on Gaussian process classification and Bayesian inference. Its performance suggests that non-verbal channels carrying affective cues can help provide important information to a system for formulating a more intelligent response.

Exploring the Assistance Dilemma in Experiments with Cognitive Tutors

Abstract: Intelligent tutoring systems are highly interactive learning environments that have been shown to improve upon typical classroom instruction. Cognitive Tutors are a type of intelligent tutor based on cognitive psychology theory of problem solving and learning. Cognitive Tutors provide a rich problem-solving environment with tutorial guidance in the form of step-by-step feedback, specific messages in response to common errors, and on-demand instructional hints. They also select problems based on individual student performance. The learning benefits of these forms of interactivity are supported, to varying extents, by a growing number of results from experimental studies. As Cognitive Tutors have matured and are being applied in new subject-matter areas, they have been used as a research platform and, particularly, to explore interactive methods to support metacognition. We review experiments with Cognitive Tutors that have compared different forms of interactivity and we reinterpret their results as partial answers to the general question: How should learning environments balance information or assistance giving and withholding to achieve optimal student learning? How best to achieve this balance remains a fundamental open problem in instructional science. We call this problem the “assistance dilemma” and emphasize the need for further science to yield specific conditions and parameters that indicate when and to what extent to use information giving versus information withholding forms of interaction.

Toward an Affect-Sensitive AutoTutor

Abstract: Here, we consider the possibility of enabling AutoTutor, an intelligent tutoring system, to process learners' affective and cognitive states. AutoTutor is a fully automated computer tutor that simulates human tutors and converses with students in natural language.

The effects of the classroom flip on the learning environment: a comparison of learning activity in a traditional classroom and a flip classroom that used an intelligent tutoring system

Abstract: With the rise of technology use in college classrooms, many professors are open to structuring their classrooms in innovative ways. The classroom flip (or inverted classroom) is one such innovative classroom structure that moves the lecture outside the classroom via technology and moves homework and practice with concepts inside the classroom via learning activities. This research compares the classroom flip and the traditional lecture/homework structure in two different college level introductory statistics classrooms. In the classroom flip classroom, an intelligent tutoring system (ITS) was used to deliver the lecture content outside the classroom. Students completed active learning projects in the classroom that often required the use of a spreadsheet computer program to help students work with the concepts in the course. In the lecture/homework classroom, students attended lectures on course content that included PowerPoint slides, and then students practiced with the course concepts by completing homework from their books outside of class. The learning environment and the learning activity in both classrooms are investigated in this study with respect to activity theory and learning environments research. Students were given the College and University Classroom Environment Inventory (CUCEI) to measure both their learning environment preferences and their learning environment experiences. In addition, data were collected via field notes, classroom transcripts, student interviews, student focus groups, researcher journal entries, and student reflections. The quantitative data were analyzed using t-tests and MANOVA, and the qualitative data were analyzed using grounded theory methods. The findings of this research show that classroom flip students were less satisfied with how the structure of the classroom oriented them to the learning tasks in the course. The variety of learning activities in the flipped classroom contributed to an unsettledness among students that traditional classroom students did not experience. Finally, the concept of student comfortability with learning activity is presented and developed in light of learning environments research.

Modeling and understanding students' off-task behavior in intelligent tutoring systems

Abstract: We present a machine-learned model that can automatically detect when a student using an intelligent tutoring system is off-task, i.e., engaged in behavior which does not involve the system or a learning task. This model was developed using only log files of system usage (i.e. no screen capture or audio/video data). We show that this model can both accurately identify each student's prevalence of off-task behavior and can distinguish off-task behavior from when the student is talking to the teacher or another student about the subject matter. We use this model in combination with motivational and attitudinal instruments, developing a profile of the attitudes and motivations associated with off-task behavior, and compare this profile to the attitudes and motivations associated with other behaviors in intelligent tutoring systems. We discuss how the model of off-task behavior can be used within interactive learning environments which respond to when students are off-task.

Supporting collaborative learning and problem-solving in a constraint-based CSCL environment for UML class diagrams

Abstract: We present COLLECT-UML, a constraint-based intelligent tutoring system (ITS) that teaches object-oriented analysis and design using Unified Modelling Language (UML). UML is easily the most popular object-oriented modelling technology in current practice. While teaching how to design UML class diagrams, COLLECT-UML also provides feedback on collaboration. Being one of constraint-based tutors, COLLECT-UML represents the domain knowledge as a set of constraints. However, it is the first system to also represent a higher-level skill such as collaboration using the same formalism. We started by developing a single-user ITS that supported students in learning UML class diagrams. The system was evaluated in a real classroom, and the results showed that students’ performance increased significantly. In this paper, we present our experiences in extending the system to provide support for collaboration as well as domain-level support. We describe the architecture, interface and support for collaboration in the new, multi-user system. The effectiveness of the system has been evaluated in two studies. In addition to improved problem-solving skills, the participants both acquired declarative knowledge about effective collaboration and did collaborate more effectively. The participants have enjoyed working with the system and found it a valuable asset to their learning.

Gender-Specific Approaches to Developing Emotionally Intelligent Learning Companions

Abstract: The nonverbal social behaviors of virtual learning companions and their affect and task support have gender-specific impacts on learners' frustration and self-awareness during a challenging problem-solving activity. Social bonding and affective support between teachers and learners have considerable impact on learners' performance and motivation. One way to develop a social bond with learners is to provide assistance. According to research in this area (see the sidebar "Related Work on Affective Tutoring Systems"), systems that provide affective support to frustrated users can reduce frustration. A study of expert human tutors' interactions with their students found that up to half of these interactions focus on supporting the learner's affective state. Currently, most intelligent tutoring systems provide predominantly task-based support.

Early Prediction of Student Frustration

Abstract: Affective reasoning has been the subject of increasing attention in recent years. Because negative affective states such as frustration and anxiety can impede progress toward learning goals, intelligent tutoring systems should be able to detect when a student is anxious or frustrated. Being able to detect negative affective states early, i.e., before they lead students to abandon learning tasks, could permit intelligent tutoring systems sufficient time to adequately prepare for, plan, and enact affective tutorial support strategies. A first step toward this objective is to develop predictive models of student frustration. This paper describes an inductive approach to student frustration detection and reports on an experiment whose results suggest that frustration models can make predictions early and accurately.

Improving Student Performance Using Self-Assessment Tests

Abstract: Testing is the most generic and perhaps most widely used mechanism for student assessment. Most tests are based on the classical test theory, which says that a student's score is the sum of the scores obtained in all questions plus some kind of error. The most relevant is that the student test result depends heavily on the individual's learning preferences or abilities and also on the actual test's format. According to this theory, tests aren't necessarily useful in intelligent educational systems, which require accurately obtaining the student's knowledge state to guide the learning process. Yet the Web has created a new generation of intelligent systems-adaptive hypermedia systems which offer new types of instructional interaction. Educational AHSs adapt the learning process on the basis of the student's learning preferences, knowledge, and availability. One such Web-based tool is Siette (the system of intelligent evaluation using rests), which infers student knowledge using adaptive testing.

What Evidence Matters? A randomized field trial of Cognitive Tutor Algebra I

Abstract: Efforts to improve performance in mathematics have put pressure on educational evaluators to improve the rigor of their evaluation designs. This paper reports the results of a rigorous evaluation of the Cognitive Tutor Algebra I curriculum, which is substantially based on an intelligent tutoring system. We emphasize the importance of presenting details of the design, implementation and analysis of the study in order to ensure the best possibility of improvement over time.

Mind and Body: Dialogue and Posture for Affect Detection in Learning Environments

Abstract: We investigated the potential of automatic detection of a learner's affective states from posture patterns and dialogue features obtained from an interaction with AutoTutor, an intelligent tutoring system with conversational dialogue. Training and validation data were collected from the sensors in a learning session with AutoTutor, after which the affective states of the learner were rated by the learner, a peer, and two trained judges. Machine learning experiments with several standard classifiers indicated that the dialogue and posture features could individually discriminate between the affective states of boredom, confusion, flow (engagement), and frustration. Our results also indicate that a combination of the dialogue and posture features does improve classification accuracy. However, the incremental gains associated with the combination of the two sensors were not sufficient to exhibit superadditivity (i.e., performance superior to an additive combination of individual channel). Instead, the combination of posture and dialogue reflected a modest amount of redundancy among these channels.

Modeling learning patterns of students with a tutoring system using Hidden Markov Models

Abstract: The current paper focuses on modeling actions of high school students with a mathematics tutoring system with Hidden Markov Models. The results indicated that including a hidden state estimate of learner engagement increased the accuracy and predictive power of the models, both within and across tutoring sessions. Groups of students with distinct engagement trajectories were identified, and findings were replicated in two independent samples. These results suggest that modeling learner engagement may help to increase the effectiveness of intelligent tutoring systems since it was observed that engagement trajectories were not predicted by prior math achievement of students.

LIM-G: Learner-initiating instruction model based on cognitive knowledge for geometry word problem comprehension

Abstract: Computer-assisted instruction systems have been broadly applied to help students solve math word problem. The majority of such systems, which are based on an instructor-initiating instruction strategy, provide pre-designed problems for the learners. When learners are asked to solve a word problem, the system will instruct the learners what to do. However, systems employing an instructor-initiating instruction strategy offer little help to advanced learners or to learners encountering problems that are not in the pre-designed database. Therefore, in this study, a learner-initiating instruction model (LIM-G) is proposed to help learners' comprehension of geometry word problems. Geometry word problems are math word problems involving geometric concepts. Many researches indicate that learners encounter difficulties while comprehending math word problems. In this model, a learner can seek help with any geometry word problem he is interested in. Based on a learner-initiating instruction strategy, LIM-G first comprehends the problem and then gives the learner the telegraphic and diagrammatic representations of the problem, which are more intuitive to understand. For LIM-G, the comprehension mechanism plays a critical role in solving word problems. For this study, a system is built based on LIM-G. In this system, the cognitive knowledge needed for comprehending geometry word problem is constructed with an ontology-based tool called InfoMap. Using cognitive knowledge and frame-template structures, the system can extract the relevant concepts in geometry word problems for comprehension.

Intelligent Web-based Tutoring System with Personalized Learning Path Guidance

Abstract: Personalized curriculum sequencing is an important research issue for web-based learning systems because no fixed learning paths will be appropriate for all learners. Therefore, many researchers focused on developing e-learning systems with personalized learning mechanisms to assist online web-based learning and adaptively provide learning paths in order to promote the learning performance of individual learners. Generally, inappropriate courseware leads to learner cognitive overload or disorientation during learning processes, thus reducing learning performance. Therefore, compared with the freely browsing learning mode used in most web-based learning systems, this paper assesses whether the proposed genetic-based personalized e-learning system which can generate appropriate learning paths according to the incorrect testing responses of individual learners in a pre-test provides benefits in terms of learning performance promotion. Experiment results indicated that applying the proposed genetic-based personalized e-learning system for Web-based learning is superior to the freely browsing learning mode because of high quality and concise learning path for individual learners.

COMET: A Collaborative Tutoring System for Medical Problem-Based Learning

Abstract: This paper discussed about the developed collaborative intelligent tutoring system for medical PBL called Comet (collaborative medical tutor). Comet uses Bayesian networks to model the knowledge and activity of individual students as well as small groups. It applies generic tutoring algorithms to these models and generates tutorial hints that guide problem solving. An early laboratory study shows a high degree of agreement between the hints generated by Comet and those of experienced human tutors. Evaluations of Comet's clinical-reasoning model and the group reasoning path provide encouraging support for the general framework.

Content Matters: An Investigation of Feedback Categories within an ITS

Abstract: The primary goal of this study was to investigate the role of feedback in an intelligent tutoring system (ITS) with natural language dialogue One core component of tutorial dialogue is feedback, which carries the primary burden of informing students of their performance AutoTutor is an ITS with tutorial dialogue that was developed at the University of Memphis This article addresses the effectiveness of two types of feedback (content & progress) while college students interact with AutoTutor on conceptual physics Content feedback provides qualitative information about the domain content and its accuracy as it is covered in a tutoring session Progress feedback is a quantitative assessment of the student's advancement through the material being covered (ie, how far the student has come and how much farther they have to go) A factorial design was used that manipulated the presence or absence of both feedback categories (content & progress) Each student interacted with one of four different versions of AutoTutor that varied the type of feedback Data analyses showed significant effects of feedback on learning and motivational measures, supporting the notion that “content matters” and the adage “no pain, no gain”

Can a Polite Intelligent Tutoring System Lead to Improved Learning Outside of the Lab

Abstract: In this work we are investigating the learning benefits of e-Learning principles (a) within the context of a web-based intelligent tutor and (b) in the “wild,” that is, in real classroom (or homework) usage, outside of a controlled laboratory. In the study described in this paper, we focus on the benefits of politeness, as originally formulated by Brown and Levinson and more recently studied by Mayer and colleagues. We test the learning benefits of a stoichiometry tutor that provides polite problem statements, hints, and error messages as compared to one that provides more direct feedback. Although we find a small, but not significant, trend toward the polite tutor leading to better learning gains, our findings do not replicate that of Wang et al., who found significant learning gains through polite tutor feedback. While we hypothesize that an e-Learning principle such as politeness may not be robust enough to survive the transition from the lab to the “wild,” we will continue to experiment with the polite stoichiometry tutor.

Intelligent Tutoring for Interpersonal and Intercultural Skills

Abstract: We describe some key issues involved in building an intelligent tutoring system for the ill-defined domain of interpersonal and intercultural skill acquisition. We discuss the consideration of mixed-result actions (actions with pros and cons), categories of actions (e.g., required steps vs. rules of thumb), the role of narrative, and reflective tutoring, among other topics. We present these ideas in the context of our work on an intelligent tutor for ELECT BiLAT, a game-based system to teach cultural awareness and negotiation skills for bilateral engagements. The tutor provides guidance in two forms: (1) as a coach that gives hints and feedback during an engagement with a virtual character, and (2) during an after-action review to help the learner reflect on their choices. Learner activities are mapped to learning objectives, which include whether the actions represent positive or negative evidence of learning. These underlie an expert model, student model, and models of coaching and reflective tutoring that support the learner. We describe several other cultural and interpersonal training systems that situate learners in goal-based social contexts that include interaction with virtual characters and automated guidance. Finally, our future work includes evaluations of learning, expansion of the coach and reflective tutoring strategies, and integration of deeper knowledge-based resources that capture more nuanced cultural aspects of interaction.

Explicit Reflection in Prolog-Tutor

Abstract: This paper describes a reflection-based approach for open learner modeling (OLM). Tutoring dialogues are used by learners to explicitly reveal their own knowledge state to themselves. Dewey's theory of reflective thinking is used to create tutorial strategies which govern these dialogues. Drake's specification of critical thinking, associated to a defined set of skills, is used to define tutoring tactics implementing these strategies. The main contribution of this approach to OLM is that it provides a set of principled and reusable tutorial strategies and tactics to promote reflection, as they are based on domain independent theories. Furthermore, an evaluation of such a principled approach to OLM is straightforward in certain cases, as it refers to theories which already provide evaluation criteria. The approach is integrated in Prolog-Tutor, an existing intelligent tutoring system for Logic Programming. This paper presents a qualitative study of the resulting system, based on think-aloud protocols. A result analysis reveals that explicitly fostering reflection supports reflection based OLM and provides landmarks to explain its manifestations. However, the results also suggest that this openness may be less helpful when used by learners who have already honed a high level of proficiency in logic programming.

Implementation and performance evaluation of parameter improvement mechanisms for intelligent e-learning systems

Abstract: In recent years, designing useful learning diagnosis systems has become a hot research topic in the literature. In order to help teachers easily analyze students' profiles in intelligent tutoring system, it is essential that students' portfolios can be transformed into some useful information to reflect the extent of students' participation in the curriculum activity. It is observed that students' portfolios seldom reflect students' actual studying behaviors in the learning diagnosis systems given in the literature; we thus propose three kinds of learning parameter improvement mechanisms in this research to establish effective parameters that are frequently used in the learning platforms. The proposed learning parameter improvement mechanisms can calculate the students' effective online learning time, extract the portion of a message in discussion section which is strongly related to the learning topics, and detect plagiarism in students' homework, respectively. The derived numeric parameters are then fed into a Support Vector Machine (SVM) classifier to predict each learner's performance in order to verify whether they mirror the student's studying behaviors. The experimental results show that the prediction rate for the SVM classifier can be increased up to 35.7% in average after the inputs to the classifier are ''purified'' by the learning parameter improvement mechanisms. This splendid achievement reveals that the proposed algorithms indeed produce the effective learning parameters for commonly used e-learning platforms in the literature.

Diagnostic, predictive and compositional modeling with data mining in integrated learning environments

Abstract: Models represent a set of generic patterns to test hypotheses. This paper presents the CogMoLab student model in the context of an integrated learning environment. Three aspects are discussed: diagnostic and predictive modeling with respect to the issues of credit assignment and scalability and compositional modeling of the student profile in the context of an intelligent tutoring system/adaptive hypermedia learning system architectural pattern. The SOM-PCA, a collaborative-based data mining approach, is shown to be reusable for all three purposes above, enabling fast, objective implementations without requiring much intensive data collection.

A pedagogical framework to integrate learning style into intelligent tutoring systems

Abstract: Educational systems can be more adaptive and effective when they incorporate learning style models. Developing a learning style based system is not a trivial task and presents challenges such as selecting the appropriate learning style model and instrument, creating course content consistent with the various learning styles, and determining the level and degree of adaptation of domain content. We present a pedagogical framework that makes it possible to integrate learning style into an intelligent tutoring system. This domain independent framework is based on the Felder-Silverman learning style model and has been designed in the context of CIMEL-ITS, which helps students learn object-oriented design using UML.

Emerging Technologies in Physics Education

Abstract: Three emerging technologies in physics education are evaluated from the interdisciplinary perspective of cognitive science and physics education research. The technologies—Physlet Physics, the Andes Intelligent Tutoring System (ITS), and Microcomputer-Based Laboratory (MBL) Tools—are assessed particularly in terms of their potential at promoting conceptual change, developing expert-like problem-solving skills, and achieving the goals of the traditional physics laboratory. Pedagogical methods to maximize the potential of each educational technology are suggested.

Integrating iSTART into a High School Curriculum

Abstract: Integrating iSTART into a High School Curriculum Courtney M. Bell (cbell@mail.psyc.memphis.edu) Danielle S. McNamara (d.mcnamara@mail.psyc.memphis.edu) Institute for Intelligent Systems University of Memphis Memphis, TN 38152 Active Reading and Thinking (iSTART) into their science classrooms and curriculum. Abstract This study examines the viability in the classroom of a tutoring system called Interactive Strategy Training for Active Reading and Thinking (iSTART). This study investigated the effects of teacher-guided and iSTART- guided extended practice (following initial reading strategy training with iSTART) including 78 high school students from four biology classes. Eight high school teachers were also trained to administer reading strategy training. The results supported the conclusion that teachers can successfully integrate educational technology in such a way that it compliments their traditional teaching roles while helping to meet the needs of their students. Intelligent Tutoring Systems Intelligent tutoring systems are part of the advancements in educational technology aimed at promoting student- centered learning. As an outgrowth of earlier computer- aided instruction systems (Lajoie & Azevedo, 2005), intelligent tutoring systems are designed to capitalize on the power of one-to-one tutoring. Research by Cohen, Kulik, and Kulik (1982) indicates that when compared to traditional classroom instruction, one-to-one tutoring by untrained tutors, such as peers, cross-age tutors, or paraprofessionals, can produce an effect size for learning of .4 sigma (i.e., .4 standard deviations). Research using trained tutors suggests varying effects. For example, Bloom (1984) reported an effect size of 2 sigma (2.0 standard deviations) for math skills training, whereas VanLehn and colleagues (2007) reported an effect size of only 1 sigma (1.0 standard deviation) for physics tutoring. Despite these variations, research indicates that overall, one-to-one tutoring is effective in producing learning gains but impractical to implement on a large scale because of cost and time requirements. Intelligent tutoring systems can provide cost-effective one-to-one tutoring which is adaptable to individual students’ needs and personalizable (Tsiriga & Virvou, 2004). With the help of a student model that is dynamically monitored and updated using assessment tasks, intelligent tutors are able to provide students with adaptive feedback (Lajoie & Azevedo, 2005). This feedback guides students in correcting misconceptions and errors while helping them to effectively progress through the system (Graesser et al., 2004). iSTART is based on a human-delivered intervention called SERT (McNamara, 2004). It is an automated reading strategy trainer that teaches students to self- explain texts using five reading comprehensions strategies: comprehension monitoring, paraphrasing, elaboration, prediction, and bridging (McNamara et al., 2004). The system consists of both vicarious and interactive components to enhance learning and also consists of three phases: an introduction, demonstration, and practice, which are guided by pedagogical agents. In the introduction, students vicariously learn the five reading strategies by watching the instructor agent, Dr. Julie, use examples and definitions to teach two student agents, Mike and Julie. A short quiz follows each Keywords: Intelligent tutoring systems; iSTART; AutoTutor; classroom; curriculum; educational technology; artificial intelligence; education; science. Introduction As a result of educational reforms and new standards, educational goals and instructional methods are changing. Traditionally, school districts defined their goals and methods in terms of students being exposed to large amounts of declarative knowledge - the more, the better. And, students’ understanding and knowledge have generally been assessed in terms of explicit recall, primarily relying on fill in the blank and multiple choice tests: assessments that fail to assess deep level understanding. These techniques have often been supplemented by skill-based technologies centering on repetitive drills and practices that lack the benefits of feedback, adaptation, and knowledge construction. More recently, school districts have begun adopting instructional measures that train students to learn, train students in methods of research, help students develop the motivation to pursue personal enrichment, and train students to be creative and innovative (Domingo et al., 2002). Consequently, educational technology is also changing, and must change to adapt to the evolving understanding of how to enhance the learning process. Although policy-makers, educators, and researchers have invested large amounts of resources to meet the technological changes, successful integration at the rates hoped for has yet to occur for a number of reasons including a lack of teacher training as well as teachers’ fears of replacement and threats to their traditional roles. Thus, in this study, we examine how training influences teachers’ ability to successfully integrate an intelligent tutoring system called Interactive Strategy Training for

Advances in Intelligent Tutoring Systems: Problem-solving Modes and Model of Hints

Abstract: The paper focuses on the issues of providing an adaptive support for learners in intelligent tutoring systems when learners solve practical problems. The results of the analysis of support policies of learners in the existing intelligent tutor- ing systems are given and the revealed problems are emphasized. The concept and the architectural parts of an intelligent tutoring system are defined. The approach which provides greater adaptive abilities of systems of such kind offering two modes of problem-solving and using a two-layer model of hints is described. It is being implemented in the intelligent tutoring system for the Minimax algorithm at present. In accordance with the proposed approach the learner solves problems in the mode which is the most appropriate for him/her and receives the most suitable hint.

Promoting Learning in Mathematics: Script Support for Collaborative Problem Solving with the Cognitive Tutor Algebra

Abstract: Dejana Diziol, Nikol Rummel, Hans Spada, Bruce McLaren Institute of Psychology, University of Freiburg, Germany Human Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA, USA We combined two different instructional methods both of which have been shown to improve students’ learning in mathematics: Learning with intelligent tutoring systems (Koedinger, Anderson, Hadley, & Mark, 1997) and collaborative problem solving (Berg, 1993). The problem-solving guidance provided by an intelligent tutoring system is effective, but because it places emphasis on learning problem solving skills, a deep understanding of underlying mathematical concepts is not necessarily achieved (Anderson, Corbett, Koedinger, & Pelletier, 1995). Collaborative activities can yield elaboration of learning content (Teasley, 1995) and thus increase the potential for the acquisition of deep knowledge, but students are not always able to effectively meet the challenges of a collaborative setting and tap this potential (Rummel & Spada, 2005). Collaboration scripts that prompt fruitful interaction have proven effectively in supporting collaborative learning (Kollar, Fischer & Hesse, in press). We believe that by combining intelligent tutoring and collaborative learning we could foster the advantages of both instructional methods and overcome their disadvantages. Collaborative interaction could augment the effects of an intelligent tutoring system by promoting deeper elaboration, and script support integrated in the tutoring environment could provide guidance to students as they collaborate and thus improve the quality of their collaboration.

Developing Fine-Grained Transfer Models in the ASSISTment System

Abstract: In Massachusetts, similar to many states, teachers are being asked to use state mandated assessments in a data-driven manner to help their students meet state standards. However, teachers want feedback on student performance much more often than once a year and they also want better feedback than they currently receive. For instance, while the number of Mathematics skills and concepts that a student needs to acquire is on the order of hundreds, the feedback on the Massachusetts Comprehensive Assessment System (MCAS) test to principals, teachers, parents, and students is broken down into only 5 mathematical reporting categories: Algebra, Number Sense, Geometry, Data Analysis and Measurement. In this article, we describe our attempt to create a fine-grained transfer model for 8th grade math based on the skills needed to take the Math MCAS exam and how we use this model in a web-based intelligent tutoring system called the ASSISTment system.

CALMsystem: A Conversational Agent for Learner Modelling

Abstract: This paper describes a system which incorporates natural language technologies, database manipulation and educational theories in order to offer learners a Negotiated Learner Model, for integration into an Intelligent Tutoring System. The system presents the learner with their learner model, offering them the opportunity to compare their own beliefs regarding their capabilities with those inferred by the system. A conversational agent, or “chatbot” has been developed to allow the learner to negotiate over the representations held about them using natural language. The system aims to support the metacognitive goals of self-assessment and reflection, which are increasingly seen as key to learning and are being incorporated into UK educational policy. The paper describes the design of the system, and reports a user trial, in which the chatbot was found to support users in increasing the accuracy of their self-assessments, and in reducing the number of discrepancies between system and user beliefs in the learner model. Some lessons learned in the development have been highlighted and future research and experimentation directions are outlined.

EpiList: An Intelligent Tutoring System Shell for Implicit Development of Generic Cognitive Skills That Support Bottom-Up Knowledge Construction

Abstract: Current research efforts have shifted from the development of intelligent tutoring systems (ITSs) that focus on the teaching of "content" knowledge to those that focus on teaching cognitive skills. This shift is seen as necessary because cognitive skills are increasingly recognized by educational establishments as the foundation for knowledge acquisition, comprehension, and application. Knowledge construction is a cognitive skill and can be broadly divided into "top-down" and "bottom-up" approaches. The former splits a concept to form subordinate concepts, while the latter one groups concepts together to form a superordinate concept. Both approaches require the skill of classification and form different semantic networks or classification schemes with different levels of significance and suitability. List-making games operate within a bottom-up environment, where one has to arrange a list of items according to their respective categories. EpiList is developed along the line of a list-making game. It requires the student to suitably arrange items into categories that they have selected from a given list of categories. EpiList has employed both inductive and deductive teaching strategies to tutor the students and implicitly teach them the skills of generalization and comparison. This is achieved through the use of rules and algorithms. The rules and algorithms focus not only on the incorrect categorization of items but also on the migration of one classification scheme to another scheme that is more significant and suitable under the current teaching context. This paper computationally translates the teaching of cognitive skills into simple sets and represents the instructional process in terms of rules and algorithms operating on these sets. The field evaluations of EpiList demonstrated its capability to develop generic cognitive skills