Showing papers on "Intelligent tutoring system published in 2005"

AutoTutor: an intelligent tutoring system with mixed-initiative dialogue

Abstract: AutoTutor simulates a human tutor by holding a conversation with the learner in natural language. The dialogue is augmented by an animated conversational agent and three-dimensional (3-D) interactive simulations in order to enhance the learner's engagement and the depth of the learning. Grounded in constructivist learning theories and tutoring research, AutoTutor achieves learning gains of approximately 0.8 sigma (nearly one letter grade), depending on the learning measure and comparison condition. The computational architecture of the system uses the .NET framework and has simplified deployment for classroom trials.

The Andes Physics Tutoring System: Lessons Learned

Abstract: The Andes system demonstrates that student learning can be significantly increased by upgrading only their homework problem-solving support. Although Andes is called an intelligent tutoring system, it actually replaces only the students' pencil and paper as they do problem-solving homework. Students do the same problems as before, study the same textbook, and attend the same lectures, labs and recitations. Five years of experimentation at the United States Naval Academy indicates that Andes significantly improves student learning. Andes' key feature appears to be the grain-size of interaction. Whereas most tutoring systems have students enter only the answer to a problem, Andes has students enter a whole derivation, which may consist of many steps, such as drawing vectors, drawing coordinate systems, defining variables and writing equations. Andes gives feedback after each step. When the student asks for help in the middle of problem-solving, Andes gives hints on what's wrong with an incorrect step or on what kind of step to do next. Thus, the grain size of Andes' interaction is a single step in solving the problem, whereas the grain size of a typical tutoring system's interaction is the answer to the problem. This report is a comprehensive description of Andes. It describes Andes' pedagogical principles and features, the system design and implementation, the evaluations of pedagogical effectiveness, and our plans for dissemination.

Combining Software Games with Education: Evaluation of its Educational Effectiveness

Abstract: Computer games are very popular among children and adolescents. In this respect, they could be exploited by educational software designers to render educational software more attractive and motivating. However, it remains to be explored what the educational scope of educational software games is. In this paper, we explore several issues concerning the educational effectiveness, appeal and scope of educational software games through an evaluation study of an Intelligent Tutoring System (ITS) that operates as a virtual reality educational game. The results of the evaluation show that educational virtual reality games can be very motivating while retaining or even improving the educational effects on students. Moreover, one important finding of the study was that the educational effectiveness of the game was particularly high for students who used to have poor performance in the domain taught prior to their learning experience with the game.

The Andes Physics Tutoring System: Five Years of Evaluations

Abstract: Andes is a mature intelligent tutoring system that has helped hundreds of students improve their learning of university physics. It replaces pencil and paper problem solving homework. Students continue to attend the same lectures, labs and recitations. Five years of experimentation at the United States Naval Academy indicates that it significantly improves student learning. This report describes the evaluations and what was learned from them.

Teaching the tacit knowledge of programming to noviceswith natural language tutoring

Abstract: For beginning programmers, inadequate problem solving and planning skills are among the most salient of their weaknesses. In this paper, we test the efficacy of natural language tutoring to teach and scaffold acquisition of these skills. We describe ProPL (Pro-PELL), a dialogue-based intelligent tutoring system that elicits goal decompositions and program plans from students in natural language. The system uses a variety of tutoring tactics that leverage students' intuitive understandings of the problem, how it might be solved, and the underlying concepts of programming. We report the results of a small-scale evaluation comparing students who used ProPL with a control group who read the same content. Our primary findings are that students who received tutoring from ProPL seem to have developed an improved ability to solve the composition problem and displayed behaviors that suggest they were able to think at greater levels of abstraction than students in the read-only group.

From objects-first to design-first with multimedia and intelligent tutoring

Abstract: "Objects-first" is an increasingly popular strategy for teaching object-oriented programming by introducing the concepts of objects, classes, and instances before procedural elements of a programming language. Still, this approach emphasizes coding rather than other critical aspects of software development, notably problem-solving and design. We propose a "design-first" curriculum, which subsumes an objects-first approach into lessons that also introduce object-oriented analysis and design, using elements of UML before implementing any code. We also present CIMEL ITS, an intelligent tutoring system that uses the design-first approach to help students of various learning styles in a CS1 course. It interfaces with an IDE we have chosen specifically to support the design-first curriculum, and CIMEL, multimedia courseware which has been shown to be effective in helping students learn object-oriented programming concepts.

Advanced Geometry Tutor: An intelligent tutor that teaches proof-writing with construction

Abstract: Two problem solving strategies, forward chaining and backward chaining, were compared to see how they affect students' learning of geometry theorem proving with construction. In order to determine which strategy accelerates learning the most, an intelligent tutoring system, the Advanced Geometry Tutor, was developed that can teach either strategy while controlling all other instructional variable. 52 students were randomly assigned to one of the two strategies. Although computational modeling suggests an advantage for backwards chaining, especially on construction problems, the result shows that (1) the students who learned forward chaining showed better performance on proof-writing, especially on the proofs with construction, than those who learned backward chaining, (2) both forward and backward chaining conditions wrote wrong proofs equally frequently, and (3) the major reason for the difficulty in applying backward chaining appears to lie in the assertion of premises as unjustified propositions (i.e., subgoaling).

Knowledge-based web-enabled agents and intelligent tutoring systems

Abstract: Intelligent tutoring systems have been in existence for decades, and their characteristics can be beneficially applied in environments utilizing information and communication technology (ICT). The "intelligence" in these systems is seen through the way these systems adapt themselves to the characteristics of the students, such as speed of learning, specific areas in which the student excels as well as falls behind, and rate of learning as more knowledge is learned. In such intelligent learning environments, the agent or set of agents can be modeled to perform pedagogical tasks. This paper considers the necessary characteristics that constitute a good intelligent tutoring system. This paper introduces a framework incorporating an incremental machine-learning approach to capture 1) the dynamics of knowledge creation in the domain of interest and 2) the learned-knowledge content of the student over time. Some of the components of the proposed system are illustrated using examples from an introductory course on database design.

Feedback Micro-engineering in EER-Tutor

Abstract: Although existing educational systems are based on various learning theories, these theories are rarely used when developing feedback. Our research is based on the theory of learning from performance errors, which suggests that feedback should provide long and short-term learning advantages through revision of faulty knowledge in the context of learners' errors. We hypothesized that principled, theory-based feedback would have a positive impact on learning. To test the hypothesis we performed an experiment with EER-Tutor, an intelligent tutoring system that teaches database design. The results of the study support our hypothesis: the students who learned from theory-based feedback had a higher learning rate than their peers. We conclude that learning theories should be used to formulate design guidelines for effective feedback.

Aggregation Improves Learning: Experiments in Natural Language Generation for Intelligent Tutoring Systems

Abstract: To improve the interaction between students and an intelligent tutoring system, we developed two Natural Language generators, that we systematically evaluated in a three way comparison that included the original system as well. We found that the generator which intuitively produces the best language does engender the most learning. Specifically, it appears that functional aggregation is responsible for the improvement.

A Knowledge Acquisition System for Constraint-based Intelligent Tutoring Systems

Abstract: Building a domain model consumes a major portion of the time and effort required for building an Intelligent Tutoring System. Past attempts at reducing the knowledge acquisition bottleneck by automating the knowledge acquisition process have focused on procedural tasks. We present CAS (Constraint Acquisition System), an authoring system for automatically acquiring the domain model for non-procedural as well as procedural constraint-based tutoring systems. CAS follows a four-phase approach: building a domain ontology, acquiring syntax constraint directly from it, generating semantic constraints by learning from examples and validating the generated constraints. This paper describes the knowledge acquisition process and reports on results of a preliminary evaluation. The results have been encouraging and further evaluations are planned.

A student model for object-oriented design and programming

Abstract: "Objects-first" is an increasingly popular strategy for teaching object-oriented programming by introducing the concepts of objects, classes, and instances before procedural elements of a programming language. Learning object-oriented design and programming is a challenging task for many beginning students. We represent CIMEL ITS, which is an intelligent tutoring system that provides one-on-one tutoring to help beginners learn object-oriented analysis and design, using elements of UML before implementing any code. We also present a three-layered Student Model which supports adaptive tutoring by inferring the problem-specific knowledge state from student solutions, the historical knowledge state of the student and cognitive reasons about why the student makes an error.

Intelligent virtual environments for training: an agent-based approach

Abstract: In this paper we propose an architecture for the development of Intelligent Virtual Environments for Training, which is based on a collection of cooperative software agents. The first level of the architecture is an extension of the classical Intelligent Tutoring System architecture that adds to the expert, student, tutoring and communication modules a new module which is called World Module. Several software agents compose each module. Moreover, the proposed architecture includes agents able to simulate the behavior of human students and tutors, as well as agents able to plan the procedures to be taught (given an initial state and a desired final state) prior to the tutoring process.

A probabilistic relational student model for virtual laboratories

Abstract: We have developed an intelligent tutoring system coupled with a virtual laboratory, which constitute a semi-open learning environment. This environment provides the student with the opportunity to learn through exploration within a virtual laboratory, while achieving the expected learning objectives. The key element of this environment is a novel representation for the student model based on probabilistic relational models. This student model has several advantages: flexibility, user adaptability, high modularity and facilities for model construction for different scenarios. The model keeps track of the students' knowledge at different levels of granularity, combining the performance and exploration behavior in several experiments, to decide the best way to guide the student in following experiments, and to re-categorize the students based on the results. We have implemented a tutor for a virtual robotics laboratory, and evaluated the system with an initial group of 20 students. The results show that students who explore the virtual environment with the help of the tutor have a better academic skills, and also that the predictions of the student model are generally accurate.

A Generic Tool to Browse Tutor-Student Interactions: Time Will Tell!

Abstract: A basic question in mining data from an intelligent tutoring system is, “What happened when…?” A generic tool to answer such questions should let the user specify which phenomenon to explore; explore selected events and the context in which they occurred; and require minimal effort to adapt the tool to new versions, to new users, or to other tutors. We describe an implemented tool and how it meets these requirements. The tool applies to MySQL databases whose representation of tutorial events includes student, computer, start time, and end time. It infers the implicit hierarchical structure of tutorial interaction so humans can browse it. A companion paper [1] illustrates the use of this tool to explore data from Project LISTEN's automated Reading Tutor.

Case-based tutoring systems for procedural problem solving on the www

Abstract: This study proposes a new intelligent tutoring system using case-based student modeling. The proposed system can effectively infer the state of the student's knowledge. The knowledge state is diagnosed through the cases that are generated when the student solves a problem. We have chosen a procedural learning in the physics and designed this domain. In solving this problem, the knowledge types can be divided into the declarative and the procedural knowledge. Procedural knowledge is represented as the graphical case that constitutes a set of nodes and arcs. Declarative knowledge is represented as the analytical case that constitutes attribute-value pairs. In this study, we have implemented the intelligent tutoring system using case-based student model. We have estimated the performance between the human expert and the proposed system to prove the validity of this study. As a result, we have found that the inference method of the proposed system is similar to the human expert.

Web-based modules for programmable logic controller education

Abstract: This study describes the Virtual Programmable Logic Controller (Virtual PLC), a web-based system for PLC education that consists of (1) educational simulations to help students visualize abstract concepts, practice programming and device interfacing skills, and understand problem-solving processes; and (2) a simple intelligent tutoring system. Results from two preliminary evaluations are also presented. Index Terms—PLC, intelligent tutoring system, simulation, manufacturing engineering education. © 2005 Wiley Periodicals, Inc. Comput Appl Eng Educ 13: 266–279, 2005; Published online in Wiley InterScience (www.interscience.wiley.com); DOI 10.1002/cae.20052

A Constraint-Based Tutor for Learning Object-Oriented Analysis and Design using UML

Abstract: COLLECT-UML is an intelligent tutoring system that teaches Object-Oriented design using Unified Modelling Language (UML). UML is one of the most popular techniques used in the design and development of Object-Oriented systems nowadays. The Constraint-Based Modelling (CBM) has been used successfully in several systems and they have proved to be extremely effective in evaluations performed in real classrooms. In this paper, we present our experiences in implementing another constraint-based tutor, in the area of Object-Oriented design. We present the system's architecture and functionality and describe the results of a preliminary study with postgraduate students who interacted with the system as part of a think-aloud study. Participants felt that using the system helped them improve their UML knowledge. A full evaluation study is planned for May 2005, which aims to evaluate the interface and the effect of using the system on students' learning.

COLLECT-UML : Supporting individual and collaborative learning of UML class diagrams in a constraint-based intelligent tutoring system

Abstract: Automatic analysis of interaction and support for group learning through a distance collaborative learning system is at the forefront of educational technology. Research shows that collaborative learning provides an environment to enrich the learning process by introducing interactive partners into an educational system. Many collaborative learning environments have been proposed and used with more or less success. Researchers have been exploring different approaches to analyse and support the collaborative learning interaction. However, the concept of supporting peer-to-peer interaction in Computer-Supported Collaborative Learning (CSCL) systems is still in its infancy, and more studies are needed that test the utility of these techniques. This paper proposes an Intelligent CSCL system that uses Constraint-Based Modeling (CBM) approach, to support collaborative learning addressing both collaborative issues and task-oriented issues. The system supports the tertiary students learning Object-Oriented Analysis and Design using UML. The CBM approach is extremely efficient, and it overcomes many problems that other student modeling approaches suffer from [5]. CBM has been used successfully in several tutors supporting individual learning. The comprehensive evaluation studies of this research will provide a measure of the effectiveness of using CBM technique in Intelligent CSCL environments.

A Web-Based Intelligent Tutoring System

Abstract: A formal model of a web-based intelligent tutoring system composed of a user environment and a pedagogical environment is presented, which represents domain knowledge based on ontologies to improve the sharing and reusing of teaching materials. The system constructs the user environment based on users’ knowledge levels, learning styles, psychology characteristics, etc. in order to improve the self-adaptability and pedagogical effects of the system. Furthermore, it distinguishes information about a user and what a pedagogical agent knows about the user. Based on the pedagogical agent’s knowledge (represented by its cognitive state) about the user, a teaching process is designed for the user. Finally, the running process of the system is discussed in detail to show that the model is practicable.

Adapting to different needs in different locations: handheld computers in university education

Abstract: Educational use of handheld computers is becoming more common. It is therefore important to examine differences between standard educational interactions, and possibilities offered by handheld devices. Handheld computers allow the opportunity to study at times and locations where individualised interactions would not normally be possible or convenient. Conditions in such locations may differently affect a user's choice of task or ability to carry out an activity successfully. This paper introduces two adaptive systems: (1) a system that adapts to learner knowledge as in a standard intelligent tutoring system, but also to time availability for study and location-related features of concentration level and likelihood of interruption; (2) a system providing easy access to commonly used files, applications and tasks, according to location of use.

ReportTutor - an intelligent tutoring system that uses a natural language interface.

Abstract: ReportTutor is an extension to our work on Intelligent Tutoring Systems for visual diagnosis. ReportTutor combines a virtual microscope and a natural language interface to allow students to visually inspect a virtual slide as they type a diagnostic report on the case. The system monitors both actions in the virtual microscope interface as well as text created by the student in the reporting interface. It provides feedback about the correctness, completeness, and style of the report. ReportTutor uses MMTx with a custom data-source created with the NCI Metathesaurus. A separate ontology of cancer specific concepts is used to structure the domain knowledge needed for evaluation of the student’s input including co-reference resolution. As part of the early evaluation of the system, we collected data from 4 pathology residents who typed in their reports without the tutoring aspects of the system, and compared responses to an expert dermatopathologist. We analyzed the resulting reports to (1) identify the error rates and distribution among student reports, (2) determine the performance of the system in identifying features within student reports, and (3) measure the accuracy of the system in distinguishing between correct and incorrect report elements.

Facial signs of affect during tutoring sessions

Abstract: An emotionally intelligent tutoring system should be able to taking into account relevant aspects of the mental state of the student when providing feedback. The student’s facial expressions, put in context, could provide cues with respect to this state. We discuss the analysis of the facial expression displayed by students interacting with an Intelligent Tutoring System and our attempts to relate expression, situation and mental state building on Scherer’s component process model of emotion appraisal.

Using learning curves to mine student models

Abstract: This paper presents an evaluation study that measures the effect of modifying feedback generality in an Intelligent Tutoring System (ITS) based on Student Models. A taxonomy of the tutor domain was used to group existing knowledge elements into plausible, more general, concepts. Existing student models were then used to measure the validity of these new concepts, demonstrating that at least some of these concepts appear to be more effective at capturing what the students learned than the original knowledge elements. We then trialled an experimental ITS that gave feedback at a higher level. The results suggest that it is feasible to use this approach to determine how feedback might be fine-tuned to better suit student learning, and hence that learning curves are a useful tool for mining student models.

A semi-open learning environment for virtual laboratories

Abstract: Open learning environments often involve simulation where learners can experiment with different aspects and parameters of a given phenomenon to observe the effects of these changes. These are desirable in virtual laboratories. However, an important limitation of open learning environments is the effectiveness for learning, because it strongly depends on the learner ability to explore adequately. We have developed a semi-open learning environment for a virtual robotics laboratory based on simulation, to learn through free exploration, but with specific performance criteria that guide the learning process. We proposed a generic architecture for this environment, in which the key element is an intelligent tutoring system coupled to a virtual laboratory. The tutor module combines the performance and exploration behaviour of a student in several experiments, to decide the best way to guide his/her. We present an evaluation with an initial group of 20 students. The results show how this semi-open leraning environment can help to accelerate and improve the learning process.

Redefinition of basic modules of an intelligent tutoring system: the tutor module

Abstract: It has been noticed that during the initial semesters of Computing Engineering that the amount of human tutors is insufficient. The students/tutors ratio is very high and there is a great difference in the acquired knowledge and backgrounds. The idea is that a system could emulate the human tutor and besides provide the student with a degree of flexibility for the selection of the most adequate tutorial type. This could be a feasible solution to the stated problem. But a tutorial system should not only emulate the human tutor but besides it should be designed from an epistemological conception of what teaching Basic Programming means specially in an Engineering course due to the profile and identity of the future engineer.

An architecture for knowledge management in intelligent tutoring system

Abstract: This paper discusses a general framework for knowledge acquisition and management in an intelligent tutoring system. This system is based on "Learning by performance errors" theory stating that in a given domain knowledge there is a set of constraints that must be satisfied in order to provide the correct solution to the problem. This paper addresses the issues of representing complex and generic information that applies to multiple domains. The proposed solution provides guidelines for both the system knowledge acquisition and management based on the natural language processing platform GATE (General Architecture for Text Engineering), inductive logic programming and constraint based paradigm.

Making decisions in an intelligent tutoring system

Abstract: In computerized tutoring, the pace of instruction is related to the student's mastery levels of the learning objectives. The observable student's behavior that can be used to measure his knowledge is usually his responses to test items. Unobservable variables that are related to learner's motivation can affect learning but are difficult to quantify. In comparison with other decision-theoretic tutoring systems, the novelties of this research are: (1) the efficiency-centric approach to develop the Bayesian networks; (2) the formulation of utility values for different tutoring outcomes that are independent of past actions and to satisfy the separability condition; (3) the development of a common measure for student's mastery levels and item difficulties; and (4) the generation of optimal policies in polynomial time. A prototype web-based tutoring system, known as iTutor, incorporating the novelties has been developed for engineering mechanics. Formative evaluations of iTutor have shown encouraging results.

COLLECT-UML: supporting individual and collaborative learning of UML class diagrams in a constraint-based intelligent tutoring system

Abstract: Automatic analysis of interaction and support for group learning through a distance collaborative learning system is at the forefront of educational technology. Research shows that collaborative learning provides an environment to enrich the learning process by introducing interactive partners into an educational system. Many collaborative learning environments have been proposed and used with more or less success. Researchers have been exploring different approaches to analyse and support the collaborative learning interaction. However, the concept of supporting peer-to-peer interaction in Computer-Supported Collaborative Learning (CSCL) systems is still in its infancy, and more studies are needed that test the utility of these techniques. This paper proposes anIntelligent CSCL system that uses Constraint-Based Modeling (CBM) approach, to support collaborative learning addressing both collaborative issues and task-oriented issues. The system supports the tertiary students learning Object-Oriented Analysis and Design using UML. The CBM approach is extremely efficient, and it overcomes many problems that other student modeling approaches suffer from [5]. CBM has been used successfully in several tutors supporting individual learning.The comprehensive evaluation studies of this research will provide a measure of the effectiveness of using CBM technique in Intelligent CSCL environments.

An Algebra Subsystem for Diagnosing Students' Input in a Physics Tutoring System

Abstract: To help a student in an introductory physics course do quantitative homework problems, an intelligent tutoring system must determine information of an algebraic nature. This paper describes a subsystem which resolves such questions for Andes2. The capabilities of the subsystem would be useful for any ITS which deals with problems involving complex systems of equations. This subsystem is capable of 1) solving the systems of equations at the level of introductory physics problems, 2) checking the validity of equations the students enter, 3) investigating whether an equation is independent from a set of other equations, and if not, determining on which equations it does depend, and finally 4) providing tools to help the student with algebraic manipulations, including a "solve-tool" that solves her equations. The ability to determine dependence of equations is first used by Andes during problem generation, by providing information to that component of the ITS which generates correct solutions to the problem. Later, during tutoring, it enables the help module to model which equations the student appears to know. One new feature of this algebra subsystem is that it deals with the dimensional units of physical quantities throughout. An important change from a previous approach is in the meaning of "correctness" of an equation and in the method of determining which equations it can be derived from. The theoretical differences between the two methods, and the pros and cons of each, are discussed. Then we evaluate how the capabilities of the subsystem have affected the Andes tutor's effectiveness, with a particular emphasis on the effects of the changed method.