Adaptive Tutoring Research Articles

Intelligent technology for construction of tutoring integrated expert systems: new aspects

The main aim of this paper is to acquaint readers of the journal “Open Education” with the accumulated experience of construction and practical use in the educational process of Cybernetics Department of the National Research Nuclear University MEPhI of a special class of intelligent tutoring systems, based on the architectures of tutoring integrated expert systems. The development is carried out on the problem-oriented methodology basis and intelligent software environment of AT-TECHNOLOGY workbench. They provide automation of support of all the stages of construction and maintenance of the life cycle of such systems. In the context of basic models, methods, algorithms and tools that implement the conceptual foundations of a problem-oriented methodology, and which are evolutionarily developed and experimentally investigated in the process of constructing various architectures of training integrated expert systems, including webbased ones, some features of the generalized model of intellectual learning and its components are considered (in particular, the competence-based model of the trainee, the adaptive tutoring model, the ontology model of the course /discipline et al.) as well as methods and means of their realization in the current versions of tutoring integrated expert systems. In current versions of tutoring integrated expert systems examples of implementation of typical intelligent tutoring problems are described for the generalized ontology “Intelligent systems and technologies” (individual planning of the method of studying the training course, intelligent analysis of training tasks, intelligent support for decision making). A brief description of the conceptual foundations of the model of the intelligent software environment of the AT-TECHNOLOGY workbench is given and a description of some components of the model is presented with a focus on the basic components – intelligent planner, standard design procedures and reusable components, which provide automated support for the prototyping processes of tutoring integrated expert systems. A brief description of the models and approaches, used in the formalization of the planning and management processes of prototyping is presented. Schemes for the implementation of the standard design procedure “Construction of training IES and web-IES” in different modes of operation are described, as well as the technology of using reusable components for the development of tutoring integrated expert systems. Quantitative estimations of various components/ parameters of tutoring integrated expert systems are given and further prospects for their application are analyzed.

Adaptive Virtual Reality Training to Optimize Military Medical Skills Acquisition and Retention.

The Department of Defense has pursued the integration of virtual reality simulation into medical training and applications to fulfill the need to train 100,000 military health care personnel annually. Medical personnel transitions, both when entering an operational area and returning to the civilian theater, are characterized by the need to rapidly reacquire skills that are essential but have decayed through disuse or infrequent use. Improved efficiency in reacquiring such skills is critical to avoid the likelihood of mistakes that may result in mortality and morbidity. We focus here on a study testing a theory of how the skills required for minimally invasive surgery for military surgeons are learned and retained. Our adaptive virtual reality surgical training system will incorporate an intelligent mechanism for tracking performance that will recognize skill deficiencies and generate an optimal adaptive training schedule. Our design is modeling skill acquisition based on a skill retention theory. The complexity of appropriate training tasks is adjusted according to the level of retention and/or surgical experience. Based on preliminary work, our system will improve the capability to interactively assess the level of skills learning and decay, optimizes skill relearning across levels of surgical experience, and positively impact skill maintenance. Our system could eventually reduce mortality and morbidity by providing trainees with the reexperience they need to help make a transition between operating theaters. This article reports some data that will support adaptive tutoring of minimally invasive surgery and similar surgical skills.

Improved modeling of intelligent tutoring systems using ant colony optimization

Swarm intelligence approaches, such as ant colony optimization (ACO), are used in adaptive e-learning systems and provide an effective method for finding optimal learning paths based on self-organization. The aim of this paper is to develop an improved modeling of adaptive tutoring systems using ACO. In this model, the learning object is personalized based on learning and solving problem styles. The purposed algorithm, based on ACO, generates the adaptive optimal learning path. The algorithm describes an architecture which supports the recording, processing and presentation of collective learner behavior designed to create a feedback loop informing learners of successful paths towards the attainment of learning goals. The algorithm parameters are tuned dynamically to conform to the actual pedagogical process. The article includes the results of implementation and experiment represent this algorithm is able to provide its main purpose which is finding optimal learning paths based on learning styles and improved performance of previous adaptive tutoring systems.

Cytopathology whole slide images and adaptive tutorials for senior medical students: a randomized crossover trial.

BackgroundDiagnostic cytopathology is an essential part of clinical decision-making. However, due to a combination of factors including curriculum reform and shortage of pathologists to teach introductory cytopathology, this area of pathology receives little or no formal attention in most medical school curricula. We have previously described the successful use of efficient and effective digital learning resources, including whole slide images (WSI) and virtual microscopy adaptive tutorials (VMATs), to teach cytopathology to pathology specialist trainees – a group that had prior exposure to cytopathology in their day to day practice. Consequently, in the current study we attempted to demonstrate the efficiency and efficacy of this eLearning resource in a cohort of senior medical students that was completely naïve to the subject matter (cytopathology).MethodsWe evaluated both the quantitative and qualitative impact of these digital educational materials for learning cytopathology compared with existing resources (e-textbooks and online atlases). The senior medical students were recruited from The University of New South Wales Australia for a randomized cross-over trial. Online assessments, administered after each arm of the trial, contained questions which related directly to a whole slide image. Two categories of questions in the assessments (focusing on either diagnosis or identification of cellular features) were utilized to determine efficacy. User experience and perceptions of efficiency were evaluated using online questionnaires containing Likert scale items and open-ended questions.ResultsFor this cohort of senior medical students, virtual microscopy adaptive tutorials (VMATs) proved to be at least as effective as existing digital resources for learning cytopathology. Importantly, virtual microscopy adaptive tutorials had superior efficacy in facilitating accurate diagnosis on whole slide images. Student perceptions of VMATs were positive, particularly regarding the immediate feedback, interactivity and equity of learning which this learning resource provides.ConclusionsVirtual microscopy adaptive tutorials have the potential to improve the efficacy of learning microscopic pathology for medical students. The enhanced learning experience provided by these eLearning tools merits further investigation of their utility for other cohorts, including specialist trainees.

Social Media for Ubiquitous Learning and Adaptive Tutoring [Guest editors' introduction

The popularity and influence of social media have been continuously expanding worldwide, and a similar trend is visible in educational settings. Social media tools have been reportedly used for a variety of educational purposes and in wide-ranging contexts, bridging formal and informal, as well as individual and collaborative learning. Currently, the trend is toward the integration of social media services with mobile and ubiquitous learning and adaptive educational technologies. To provide an overview of this interplay by reviewing the applicable techniques and relevant works in the area, we supplement this editorial with a tutorial survey. In particular, the following three main topics are examined and studied here: ubiquitous learning via social media services, intelligent tutoring in adaptive e-learning, and multimedia enabled social learning. The authors also introduced the articles featured in this special issue on social media for learning.

Adaptive Tutorials Versus Web-Based Resources in Radiology: A Mixed Methods Comparison of Efficacy and Student Engagement

Diagnostic imaging is under-represented in medical curricula globally. Adaptive tutorials, online intelligent tutoring systems that provide a personalized learning experience, have the potential to bridge this gap. However, there is limited evidence of their effectiveness for learning about diagnostic imaging. We performed a randomized mixed methods crossover trial to determine the impact of adaptive tutorials on perceived engagement and understanding of the appropriate use and interpretation of common diagnostic imaging investigations. Although concurrently engaged in disparate blocks of study, 99 volunteer medical students (from years 1-4 of the 6-year program) were randomly allocated to one of two groups. In the first arm of the trial on chest X-rays, one group received access to an adaptive tutorial, whereas the other received links to an existing peer-reviewed Web resource. These two groups crossed over in the second arm of the trial, which focused on computed tomography scans of the head, chest, and abdomen. At the conclusion of each arm of the trial, both groups completed an examination-style assessment, comprising questions both related and unrelated to the topics covered by the relevant adaptive tutorial. Online questionnaires were used to evaluate student perceptions of both learning resources. In both arms of the trial, the group using adaptive tutorials obtained significantly higher assessment scores than controls. This was because of higher assessment scores by senior students in the adaptive tutorial group when answering questions related to topics covered in those tutorials. Furthermore, students indicated significantly better engagement with adaptive tutorials than the Web resource and rated the tutorials as a significantly more valuable tool for learning. Medical students overwhelmingly accept adaptive tutorials for diagnostic imaging. The tutorials significantly improve the understanding of diagnostic imaging by senior students.

Intelligent and Adaptive Tutoring Systems: How to Integrate Learners

This article is a non-expert overview of intelligent technology-based instructional machines, from the first stages of their emergence up to this date. It is attempted to demonstrate their trend of evolution, and how the advances in other related fields such as education, psychology, and computer science affected them and contributed to their progress. It starts by an account of the concept of intelligent technology-based instruction and continues by defining the notion of learner integration in such systems. Furthermore, Intelligent Tutoring Systems (ITSs) are pictured: how they evolved, their architecture, and how they contributed to the field of Adaptive Learning Systems. Finally, a number of adaptive learning platforms which are the state of the art and currently used by large numbers of actual users are introduced and described.

Cytopathology whole slide images and virtual microscopy adaptive tutorials: A software pilot

Background: The constant growth in the body of knowledge in medicine requires pathologists and pathology trainees to engage in continuing education. Providing them with equitable access to efficient and effective forms of education in pathology (especially in remote and rural settings) is important, but challenging. Methods: We developed three pilot cytopathology virtual microscopy adaptive tutorials (VMATs) to explore a novel adaptive E-learning platform (AeLP) which can incorporate whole slide images for pathology education. We collected user feedback to further develop this educational material and to subsequently deploy randomized trials in both pathology specialist trainee and also medical student cohorts. Cytopathology whole slide images were first acquired then novel VMATs teaching cytopathology were created using the AeLP, an intelligent tutoring system developed by Smart Sparrow. The pilot was run for Australian pathologists and trainees through the education section of Royal College of Pathologists of Australasia website over a period of 9 months. Feedback on the usability, impact on learning and any technical issues was obtained using 5-point Likert scale items and open-ended feedback in online questionnaires. Results: A total of 181 pathologists and pathology trainees anonymously attempted the three adaptive tutorials, a smaller proportion of whom went on to provide feedback at the end of each tutorial. VMATs were perceived as effective and efficient E-learning tools for pathology education. User feedback was positive. There were no significant technical issues. Conclusion: During this pilot, the user feedback on the educational content and interface and the lack of technical issues were helpful. Large scale trials of similar online cytopathology adaptive tutorials were planned for the future.

Combining rule-based reasoning with multi-criteria decision-making in the context of adaptive tutoring for health issues

This paper describes the development of an inference mechanism that is based on a hybrid combination of rule-based reasoning of double stereotypes and decision-making techniques. This inference mechanism has been applied in an intelligent medical tutor for atheromatosis. The tutor is called intelligent atheromatosis tutor INTATU. INTATU provides adaptive tutoring on atheromatosis for various classes of users depending on their interests, background medical knowledge and computer skills. The adaptivity results from user modelling that is based on stereotypical knowledge about potential users i.e., patients, patients' relatives, doctors, medical students, etc.. For the design of the system reasoning mechanism, and, thus, the successful incorporation of the decision-making theory, an empirical study was conducted. As soon as the full functionality of the reasoning mechanism of the system was implemented, it was evaluated in comparison to the reasoning of human experts. The results of the evaluation offer strong evidence about the effectiveness of the reasoning mechanism and the overall operation of the system.

Developing Adaptive and Intelligent Tutoring Systems (AITS)

Several adaptive and intelligent tutoring systems (AITS) have been developed with different variables. These variables were the cognitive traits, cognitive styles, and learning behavior. However, these systems neglect the importance of learner's multiple intelligences, learner's skill level and learner's feedback when implementing personalized mechanisms. In this paper, the authors propose AITS based not only on the learner's multiple intelligences, but also the changing learning performance of the individual learner during the learning process. Therefore, considering learner's skill level and learner's multiple intelligences can promote personalized learning performance. Learner's skill level is obtained from pre-test result analysis, while learner's multiple intelligences are obtained from the analysis of questionnaire. After computing learning success rate of an activity, the system then modifies the difficulty level or the presentation of the corresponding activity to update courseware material sequencing. Learning process in this system is as follows. First, the system determines learning style and characteristics of the learner by an MI-Test and then makes the model. After that it plans a pre-evaluation and then calculates the score. If the learner gets the required score, the activities will be trained. Then the learner will be evaluated by a post-evaluation. Finally the system offers guidance in learning other activities. The proposed system covers all important properties such as hypertext component, adaptive sequencing, problem- solving support, intelligent solution analysis and adaptive presentation while available systems have only some of them. It can significantly improve the learning result. In other words, it helps learners to study in “the best way.”

A Multimedia Adaptive Tutoring System for Mathematics that Addresses Cognition, Metacognition and Affect

This article describes research results based on multiple years of experimentation and real-world experience with an adaptive tutoring system named Wayang Outpost. The system represents a novel adaptive learning technology that has shown successful outcomes with thousands of students, and provided teachers with valuable information about students’ mathematics performance. We define progress in three areas: improved student cognition, engagement, and affect, and we attribute this improvement to specific components and interventions that are inherently affective, cognitive, and metacognitive in nature. For instance, improved student cognitive outcomes have been measured with pre-post tests and state standardized tests, and achieved due to personalization of content and math fluency training. Improved student engagement was achieved by supporting students’ metacognition and motivation via affective learning companions and progress reports, measured via records of student gaming of the system. Student affect within the tutor was measured through sensors and student self-reports, and supported through affective learning companions and progress reports. Collectively, these studies elucidate a suite of effective strategies to support advanced personalized learning via an intelligent adaptive tutor that can be tailored to the individual needs, emotions, cognitive states, and metacognitive skills of learners.

Can more become less? Effects of an intensive assessment environment on students’ learning performance

Online interactive systems offer the beguiling prospect of an improved environment for learning at minimum extra cost. We have developed online interactive tutorials that adapt the learning environment to the current learning status of each individual student. These Adaptive Tutorials (ATs) modify the tasks given to each student according to their previous responses. Feedback, assessment and remediation are also adapted. Over a three-year period we progressively blended ATs into notoriously challenging courses in introductory Engineering Mechanics. We assessed the impact of this initiative by reviewing three lines of data: (i) the built-in diagnostics of the system, (ii) changes in student grades from year-to-year and (iii) supplementary surveys. Generally, students liked the new blended system and grades improved. Detailed analysis revealed nuances in the measures of student learning, such as differences between high-performing and low-performing students. With these insights we are able to further adapt the system to meet the learning needs of our students.

Gender differences in the use and benefit of advanced learning technologies for mathematics.

We provide evidence of persistent gender effects for students using advanced adaptive technology while learning mathematics. This technology improves each gender’s learning and affective predispositions toward mathematics, but specific features in the software help either female or male students. Gender differences were seen in the students’ style of use of the system, motivational goals, affective needs, and cognitive/affective benefits, as well as the impact of affective interventions involving pedagogical agents. We describe 4 studies, with hundreds of students in public schools over several years, which suggest that technology responses should probably be customized to each gender. This article shows differential results before, during, and after the use of adaptive tutoring software, indicating that digital tutoring systems can be an important supplement to mathematics classrooms but that male and female students should be addressed differently. Female students were more receptive than male students to seeking and accepting help provided by the tutoring system and to spending time seeing the hints; thus, they had a consistent general trend to benefit more from it, especially when affective learning companions were present. In addition, female students expressed positively valenced emotions most often and exhibited more productive behaviors when exposed to female characters; these affective pedagogical agents encouraged effort and perseverance. This was not the case for male students, who had more positive outcomes when no learning companion was present and their worst affective and cognitive outcomes when the female character was present.

An adaptation algorithm for an intelligent natural language tutoring system

The focus of computerised learning has shifted from content delivery towards personalised online learning with Intelligent Tutoring Systems (ITS). Oscar Conversational ITS (CITS) is a sophisticated ITS that uses a natural language interface to enable learners to construct their own knowledge through discussion. Oscar CITS aims to mimic a human tutor by dynamically detecting and adapting to an individual's learning styles whilst directing the conversational tutorial. Oscar CITS is currently live and being successfully used to support learning by university students. The major contribution of this paper is the development of the novel Oscar CITS adaptation algorithm and its application to the Felder–Silverman learning styles model. The generic Oscar CITS adaptation algorithm uniquely combines the strength of an individual's learning style preference with the available adaptive tutoring material for each tutorial question to decide the best fitting adaptation. A case study is described, where Oscar CITS is implemented to deliver an adaptive SQL tutorial. Two experiments are reported which empirically test the Oscar CITS adaptation algorithm with students in a real teaching/learning environment. The results show that learners experiencing a conversational tutorial personalised to their learning styles performed significantly better during the tutorial than those with an unmatched tutorial.

Combining Expert Systems and Multiple Intelligences in an Adaptive and Intelligent Tutoring System

This paper describes an adaptive and intelligent tutoring system (AITS) based on multiple intelligences and expert system. Most of adaptive and intelligent tutoring systems based their adaptation to user’s skill level. Other learner features taken into account are background, hyperspace experience, preferences and interests. However, less attention was paid to multiple intelligences and their effects on learning. Moreover, to design AITS which can manage both different disciplinary domains and a guide for the learner is difficult. The specialization of the analysis treatments is responsible for the loss of reusability for the other disciplinary domains. To overcome these limitations, the authors will try to combine the benefits of paradigms (adaptive hypermedia, intelligent tutoring system, multiple intelligences) in order to adapt the course to the needs and intellectual abilities of each learner.

PeRSIVA: An empirical evaluation method of a student model of an intelligent e-learning environment for computer programming

In this paper an evaluation method for assessing the effectiveness, accuracy and validity of a student model was presented. Our method is called PeRSIVA and is a combination of the well-known evaluation method of Kirkpatrick and the layered evaluation framework. These well-known and commonly used evaluation techniques have been selected in order to design an accurate and correct evaluation methodology, since there are no clear guidelines in the literature for the evaluation of the student model of an adaptive tutoring system. Furthermore, PeRSIVA method was used to evaluate the hybrid student model, which combines an overlay model with stereotypes and fuzzy logic techniques, of an e-learning system. Particularly, PeRSIVA assesses the results of student modeling in students' satisfaction, performance, progress, behavior and state, as well as the validity of the conclusions drawn by the student model and the validity of the adaptation decision making. The e-learning system was used by the students of a postgraduate program in the field of informatics in the University of Piraeus and the evaluation results demonstrated learning improvements in students and adaptation success to students' needs.

Using non-verbal cues to (automatically) assess children’s performance difficulties with arithmetic problems

Intelligent tutoring systems often make use of students’ answers to adapt instruction or feedback on a task. In this paper, we explore the alternative possibility of adapting a system based on the perceived affective and cognitive state of a student. A system can potentially better adapt to the needs of each individual student by using non-verbal behavior. We used a new experimental paradigm inspired by ‘brain training’ software to collect primary school children’s answers to easy and difficult arithmetic problems and made audiovisual recordings of their answers. Adult observers rated these films on perceived difficulty level. Results showed that adults were able to correctly interpret children’s perceived level of difficulty, especially if they saw their face (compared to hearing their voice). They paid attention to features such as ‘looking away’, and ‘frowning’. Then we checked whether we could also automatically predict if the posed problem was either easy or difficult based on the first second of their response. This ‘thin-slice analysis’ could correctly predict the difficulty level in 71% of all cases. When trained on sufficiently many recordings, Adaptive Tutoring Systems should be able to detect children’s state and adapt the difficulty level of their learning materials accordingly.

An Adaptive and Intelligent Tutor by Expert Systems for Mobile Devices

Mobile Learning (M-Learning) is an emerging discipline in the area of education and educational technology. So researchers are trying to optimize and expanding its application in the field of education. The aim of this paper is to investigate the role of mobile devices and expert systems in disseminating and supporting the knowledge gained by intelligent tutors and to propose a system based on integration of intelligent M-Learning with expert systems. It acts as an intelligent tutor which can perform three processes - pre-test, learning concept and post-test - according to characteristic of the learner. The proposed system can improves the education efficiency highly as well as decreases costs. As a result, every time and everywhere (ETEW) simple and cheap learning would be provided via SMS, MMS and so on in this system. The global intention of M-Learning is to make learning “a way of being”.

A web-based adaptive tutor to teach PCR primer design

When students have varying prior knowledge, personalized instruction is desirable. One way to personalize instruction is by using adaptive e-learning to offer training of varying complexity. In this study, we developed a web-based adaptive tutor to teach PCR primer design: the PCR Tutor. We used part of the Taxonomy of Educational Objectives (the three cognitive processes: remember, understand, and apply) to design exercises of varying complexity. Using this method, we demonstrated that we were able to systematically categorize exercises. There was also a good learning effect and a positive student perception when using the PCR Tutor.

Color impact on security screening

In order to improve aviation security, many airports apply Threat Image Projection (TIP) and computer-based X-ray image interpretation training (CBT). One difference between TIP and CBT X-ray images is the algorithm used to merge virtual threat items into X-ray images of passenger bags, resulting in different color nuances. In this study, we tested the influence of merging algorithms on threat object detection performance, reaction time and confidence rating of 12 airport security screeners. The image merging algorithms of the individually adaptive CBT X-Ray Tutor were used. We have found that the hit rate was higher for TIP images compared to CBT images. Accordingly, the mean of confidence ratings was increased for TIP images. The reaction times tended to be shorter for TIP images. The results of our study indicate that the CBT merging algorithm used in this study is more realistic than the tested TIP image merging algorithm.