User modelling and user adapted interaction in an intelligent tutoring system

User modelling and user-adapted interaction are crucial to the provision of true individualised instruction, which intelligent tutoring systems strive to achieve. This paper presents how user (student) modelling and student adapted instruction is achieved in FITS, an intelligent tutoring system for the fractions domain. Some researchers have begun questioning both the need for detailed student models as well as the pragmatic possibility of building them. The key contributions of this paper are in its attempt to rehabilitate student modelling/adaptive tutoring within ITSs and in FITS's practical use of simple techniques to realise them with seemingly encouraging results; some illustrations are given to demonstrate the latter.     

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

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.     

Exploring feedback and student characteristics relevant for personalizing feedback strategies

Personalized tutoring feedback is a powerful method that expert human tutors apply when helping students to optimize their learning. Thus, research on tutoring feedback strategies tailoring feedback according to important factors of the learning process has been recognized as a promising issue in the field of computer-based adaptive educational technologies. Our paper seeks to contribute to this area of research by addressing the following aspects: First, to investigate how students' gender, prior knowledge, and motivational characteristics relate to learning outcomes (knowledge gain and changes in motivation). Second, to investigate the impact of these student characteristics on how tutoring feedback strategies varying in content (procedural vs. conceptual) and specificity (concise hints vs. elaborated explanations) of tutoring feedback messages affect students' learning and motivation. Third, to explore the influence of the feedback parameters and student characteristics on students' immediate post-feedback behaviour (skipping vs. trying to accomplish a task, and failing vs. succeeding in providing a correct answer). To address these issues, detailed log-file analyses of an experimental study have been conducted. In this study, 124 sixth and seventh graders have been exposed to various tutoring feedback strategies while working on multi-trial error correction tasks in the domain of fraction arithmetic. The web-based intelligent learning environment ActiveMath was used to present the fraction tasks and trace students' progress and activities. The results reveal that gender is an important factor for feedback efficiency: Male students achieve significantly lower knowledge gains than female students under all tutoring feedback conditions (particularly, under feedback strategies starting with a conceptual hint). Moreover, perceived competence declines from pre- to post-test significantly more for boys than for girls. Yet, the decline in perceived competence is not accompanied by a decline in intrinsic motivation, which, instead, increases significantly from pre- to post-test. With regard to the post-feedback behaviour, the results indicate that students skip further attempts more frequently after conceptual than after procedural feedback messages.     

Using a Student Model to Improve Explanation in an ITS

This paper presents the use of a student model to improve the explanations provided by an intelligent tutoring system,namely SimpleQuestl,in the domain of electronics.The method of overlay modelling is adopted to build the studdent model.The diagnosis is based on the comparison of the behaviours of the student and the expert.The student model is consulted by the “explainer”and “debugging”procedures in order to re-order the sequence of the explanation.     

Towards an Intelligent Tutoring System Architecture that Supports Remedial Tutoring

For successful teaching to take place an intelligenttutoring system has to be able to cope with anystudent errors that may occur during a tutoringinteraction. Remedial tutoring is increasingly viewedas a central part of the overall tutoring process, andrecent research calls for adaptive remedial tutoring. This paper discusses the issues of remedial tutoringthat have been proposed or implemented to supportefficient remedial tutoring. These issues serve touncover any underlying principles of remediation thatgovern remedial tutoring with intelligent tutoringsystems. In order to incorporate these principles ofremediation into intelligent tutoring systemsdevelopment processes this paper continues with thedevelopment of a model that can be employed in thedevelopment of an intelligent tutoring system that iscapable of offering remedial tutoring according tothese principles. This model is a formalisation ofremedial interventions with intelligent tutoringsystems. To demonstrate how the model can be employed indeveloping an intelligent tutoring system, INTUITION,the implementation of an existing business simulationgame, has been developed. This paper concludes with anillustration of how the model for remedial operationsprovides for remedial tutoring within INTUITION. Theevaluation of INTUITION shows that the model forremedial operations is a useful method for providingefficient remedial tutoring.     

The role of probability-based inference in an intelligent tutoring system

Probability-based inference in complex networks of interdependent variables is an active topic in statistical research, spurred by such diverse applications as forecasting, pedigree analysis, troubleshooting, and medical diagnosis. This paper concerns the role of Bayesian inference networks for updating student models in intelligent tutoring systems (ITSs). Basic concepts of the approach are briefly reviewed, but the emphasis is on the considerations that arise when one attempts to operationalize the abstract framework of probability-based reasoning in a practical ITS context. The discussion revolves around HYDRIVE, an ITS for learning to troubleshoot an aircraft hydraulics system. HYDRIVE supports generalized claims about aspects of student proficiency through probabilitybased combination of rule-based evaluations of specific actions. The paper highlights the interplay among inferential issues, the psychology of learning in the domain, and the instructional approach upon which the ITS is based.     

Reusing formalisations of legislation in a tutoring system

Statutor names an evolving Prolog program which is being developed as a knowledge-based tutoring system in the legal domain. The system utilises direct manipulation of graphical objects as a means of eliciting complex responses from the user and for providing graphical representations of complex answers to the user. It is a marriage of good interface practice and knowledge-based programming techniques which has presented a number of interesting prospects for tutoring. Perhaps the most interesting of these is the possibility of a dialog in which the student is asked to construct an argument in order to establish the truth of a particular proposition, the system then doing the same, and feedback and student modelling information being derived from a comparison of the two argument structures. This technique is not restricted in its significance to the legal domain but is applicable wherever knowledge of a subject matter can be expressed or tested by the construction of an argument. Finally, the system demonstrates the reusability of declarative knowledge by including additional modules (an expert system shall and an authoring system) with utilise the same knowledge bases as the main Statutor program itself.     

A Framework for the Initialization of Student Models in Web-based Intelligent Tutoring Systems

Initializing a student model for individualized tutoring in educational applications is a difficult task, since very little is known about a new student. On the other hand, fast and efficient initialization of the student model is necessary. Otherwise the tutoring system may lose its credibility in the first interactions with the student. In this paper we describe a framework for the initialization of student models in Web-based educational applications. The framework is called ISM. The basic idea of ISM is to set initial values for all aspects of student models using an innovative combination of stereotypes and the distance weighted k-nearest neighbor algorithm. In particular, a student is first assigned to a stereotype category concerning her/his knowledge level of the domain being taught. Then, the model of the new student is initialized by applying the distance weighted k-nearest neighbor algorithm among the students that belong to the same stereotype category with the new student. ISM has been applied in a language learning system, which has been used as a test-bed. The quality of the student models created using ISM has been evaluated in an experiment involving classroom students and their teachers. The results from this experiment showed that the initialization of student models was improved using the ISM framework.     

Formalising tutoring strategy selection in multimedia tutoring systems

Variation in tutoring strategy plays an important part in tutoring systems. The potential for providing adaptive tutoring depends initially on having a range of tutoring strategies to select from. However, in order to react effectively to the student’s needs, the system not only has to be able to offer different tutoring strategies, but to choose intelligently among them and determine which is best for an individual student at a particular moment. This paper contributes a model that formalises the process of tutoring strategy selection in tutoring systems, and shows how this is deployed in a multimedia tutoring system. The evaluation of the resulting system reveals the benefits of this model in practice.     

Student diagnosis in practice; bridging a gap

This paper presents a novel framework for looking at the problem of diagnosing a student's knowledge in an Intelligent Tutoring System. It is indicated that the input and the conceptualisation of the student model are significant for the choice of modeling technique. The framework regards student diagnosis as the process of bridging the gap between the student's input to the tutoring system, and the system's conception and representation of correct knowledge. The process of bridging the gap can be subdivided into three phases, data acquisition, transformation and evaluation, which are studied further. A number of published student modeling techniques are studied with respect to how they bridge the gap.     

Abductive Theorem Proving for Analyzing Student Explanations to Guide Feedback in Intelligent Tutoring Systems

The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive techniques for analyzing explanations, we claim that better understanding is necessary for use within tutoring systems. In this paper we motivate and describe how the system creates and uses a deeper proof-based representation of student essays in order to provide students with substantive feedback on their explanations. We describe in detail the abductive reasoner, Tacitus-lite+, that we use within the tutoring system. We also discuss evaluation results for an early version of the Why2-Atlas system and a subsequent evaluation of the theorem-proving module. We conclude with the discussion of work in progress and additional future work for deriving more benefits from a proof-based approach for tutoring applications.     

Latent Semantic Analysis for User Modeling

Latent semantic analysis (LSA) is a tool for extracting semantic information from texts as well as a model of language learning based on the exposure to texts. We rely on LSA to represent the student model in a tutoring system. Domain examples and student productions are represented in a high-dimensional semantic space, automatically built from a statistical analysis of the co-occurrences of their lexemes. We also designed tutoring strategies to automatically detect lexeme misunderstandings and to select among the various examples of a domain the one which is best to expose the student to. Two systems are presented: the first one successively presents texts to be read by the student, selecting the next one according to the comprehension of the prior ones by the student. The second plays a board game (kalah) with the student in such a way that the next configuration of the board is supposed to be the most appropriate with respect to the semantic structure of the domain and the previous student's moves.     

Representing complex knowledge in an intelligent machine tutor

Knowledge representation remains a serious issue for researchers of intelligent tutoring systems. Two areas of knowledge representation that are particularly difficult are domain and teaching knowledge. This article discusses and gives example solutions to these knowledge engineering issues and also addresses issues that relate to up-scaling existing intelligent tutoring technology to practical levels so that tutoring systems can be brought into the real world.     

A perspective on intelligent computer-assisted learning*

The recent impressive developments in intelligent knowledge-based systems design have led inevitably to proposals to design intelligent tutoring systems along similar lines. At the core of such a tutoring system is an ‘expert system’ able to perform whatever task the learner is to master. This methodology focuses on expertise, views actual student behaviour as deviant and encourages conformance to some predetermined standard. This paper describes an alternative research strategy involving the design of ‘guided discovery learning’ systems built around machine learning programs.     

基于人工情绪的智能情感网络教学系统研究

针时传统智能网络教学系统在情感教学方面的缺陷，基于人工情绪技术提出了一种Web环境下的智能情感网络教学系统结构．该系统由学习情绪模型、情绪教学模型、认知教学模型和学生模型等主要模块所构成，可以获取和识别每个学生的学习表情，并能够根据不同学生的学习情绪和学习效果，实现认知和情感相互协调的个性化教学．     

Creating cognitive tutors for collaborative learning: steps toward realization

Our long-term research goal is to provide cognitive tutoring of collaboration within a collaborative software environment. This is a challenging goal, as intelligent tutors have traditionally focused on cognitive skills, rather than on the skills necessary to collaborate successfully. In this paper, we describe progress we have made toward this goal. Our first step was to devise a process known as bootstrapping novice data (BND), in which student problem-solving actions are collected and used to begin the development of a tutor. Next, we implemented BND by integrating a collaborative software tool, Cool Modes, with software designed to develop cognitive tutors (i.e., the cognitive tutor authoring tools). Our initial implementation of BND provides a means to directly capture data as a foundation for a collaboration tutor but does not yet fully support tutoring. Our next step was to perform two exploratory studies in which dyads of students used our integrated BND software to collaborate in solving modeling tasks. The data collected from these studies led us to identify five dimensions of collaborative and problem-solving behavior that point to the need for abstraction of student actions to better recognize, analyze, and provide feedback on collaboration. We also interviewed a domain expert who provided evidence for the advantage of bootstrapping over manual creation of a collaboration tutor. We discuss plans to use these analyses to inform and extend our tools so that we can eventually reach our goal of tutoring collaboration.     

ECAL: Bridging the gap between CAL and intelligent tutoring systems

In the traditional CAL system the author generates material to be presented by computer, and the computer simply follows the explicit instructions of the author in interacting with a student. Intelligent tutoring systems rely on abstracting the implicit knowledge of a CAL system into explicit separable representations. There is a large gap between these two approaches which ECAL attempts to bridge by incorporating simple versions of ideas from artificial intelligence as extensions to a traditional CAL tool. It can be regarded as an experiment in minimalism in intelligent tutoring but it is also a practical educational tool. This paper introduces some of the authoring issues raised by ECAL, followed by a general view of the architecture of the system, and a discussion of the educational model which is implicit in ECAL. The final sections discuss the ECAL presentation system and the authoring environment.     

Using Bayesian Networks to Manage Uncertainty in Student Modeling

When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it must do both assessment and plan recognition. These modeling tasks involve a high level of uncertainty when students are allowed to follow various lines of reasoning and are not required to show all their reasoning explicitly. We use Bayesian networks as a comprehensive, sound formalism to handle this uncertainty. Using Bayesian networks, we have devised the probabilistic student models for Andes, a tutoring system for Newtonian physics whose philosophy is to maximize student initiative and freedom during the pedagogical interaction. Andes’ models provide long-term knowledge assessment, plan recognition, and prediction of students’ actions during problem solving, as well as assessment of students’ knowledge and understanding as students read and explain worked out examples. In this paper, we describe the basic mechanisms that allow Andes’ student models to soundly perform assessment and plan recognition, as well as the Bayesian network solutions to issues that arose in scaling up the model to a full-scale, field evaluated application. We also summarize the results of several evaluations of Andes which provide evidence on the accuracy of its student models.This revised version was published online in July 2005 with corrections to the author name VanLehn.     

Evaluation of a meta-tutor for constructing models of dynamic systems

Modelling is an important skill to acquire, but it is not an easy one for students to learn. Existing instructional technology has had limited success in teaching modelling. We have applied a recently developed technology, meta-tutoring, to address the important problem of teaching model construction. More specifically, we have developed and evaluated a system that has two parts, a tutor and a meta-tutor. The tutor is a simple step-based tutoring system that can give correct/incorrect feedback on student's steps and can demonstrate steps for students when asked. Because deep modelling requires difficult analyses of the quantitative relationships in a given system, we expected, and found, that students tended to avoid deep modelling by abusing the tutor's help. In order to increase the frequency of deep modelling, we added a meta-tutor that coached students to follow a learning strategy that decomposed the overall modelling problem into a series of “atomic” modelling problems. We conducted three experiments to test the effectiveness of the meta-tutor. The results indicate that students who studied with meta-tutor did indeed engage in more deep modelling practices. However, when the meta-tutor and tutor were turned off, students tended to revert to shallow modelling. Thus, the next stage of the research is to add an affective agent that will try to persuade students to persist in using the taught strategies even when the meta-tutoring and tutoring have ceased.