Intelligent Tutoring Systems Research Articles

The application of intelligent tutoring systems and social robots in autism treatment

This study examines the utilization of intelligent tutoring systems (ITS) and social robots as innovative technologies to augment the treatment of autism. In the context of artificial intelligence, these interactive systems offer personalized and engaging interventions, holding great promise for individuals on the autism spectrum. While the research in this field is still evolving and lacks maturity, early findings indicate increased engagement and potential for improved learning outcomes among autistic children. Intelligent tutoring systems, capable of adapting to individual learners, exhibit promise for delivering personalized and effective interventions. Social robots, with their interactive functionalities, provide a distinct avenue for fostering social communication and skill development. Moreover, these technologies have the potential to deliver cost-effective intervention methods, thus enhancing accessibility for children with autism and their families. However, further research, development, and integration into existing therapeutic approaches are imperative to fully actualize their potential. By harnessing the power of intelligent tutoring systems and social robots, it is possible to pave the way for more effective, personalized, and engaging autism treatment, positively impacting the lives of individuals on the autism spectrum.

Mathematics intelligent tutoring systems with handwritten input: a scoping review

Mathematics intelligent tutoring systems with handwritten input: a scoping review

Knowledge Graph-Enhanced Intelligent Tutoring System Based on Exercise Representativeness and Informativeness

In the realm of online tutoring intelligent systems, e-learners are exposed to a substantial volume of learning content. The extraction and organization of exercises and skills hold significant importance in establishing clear learning objectives and providing appropriate exercise recommendations. Presently, knowledge graph-based recommendation algorithms have garnered considerable attention among researchers. However, these algorithms solely consider knowledge graphs with single relationships and do not effectively model exercise-rich features, such as exercise representativeness and informativeness. Consequently, this paper proposes a framework, namely, the Knowledge Graph Importance-Exercise Representativeness and Informativeness Framework, to address these two issues. The framework consists of four intricate components and a novel cognitive diagnosis model called the Neural Attentive Cognitive Diagnosis model to recommend the proper exercises. These components encompass the informativeness component, exercise representation component, knowledge importance component, and exercise representativeness component. The informativeness component evaluates the informational value of each exercise and identifies the candidate exercise set E C that exhibits the highest exercise informativeness. Moreover, the exercise representation component utilizes a graph neural network to process student records. The output of the graph neural network serves as the input for exercise-level attention and skill-level attention, ultimately generating exercise embeddings and skill embeddings. Furthermore, the skill embeddings are employed as input for the knowledge importance component. This component transforms a one-dimensional knowledge graph into a multidimensional one through four class relations and calculates skill importance weights based on novelty and popularity. Subsequently, the exercise representativeness component incorporates exercise weight knowledge coverage to select exercises from the candidate exercise set for the tested exercise set. Lastly, the cognitive diagnosis model leverages exercise representation and skill importance weights to predict student performance on the test set and estimate their knowledge state. To evaluate the effectiveness of our selection strategy, extensive experiments were conducted on two types of publicly available educational datasets. The experimental results demonstrate that our framework can recommend appropriate exercises to students, leading to improved student performance.

Long short-term attentional neuro-cognitive diagnostic model for skill growth assessment in intelligent tutoring systems

Measuring student growth and providing diagnostic feedback are core components of cognitive diagnostic assessment. However, most current cognitive diagnostic models solely rely on data from a single occasion to diagnose student skill states, overlooking the substantial long-term information encapsulated in the learning history from multiple occasions. In this paper, we propose a long short-term attentional cognitive diagnostic (LS-ENCD) model for skill growth assessment in intelligent tutoring systems. Specifically, we first embed exercise and student features into high-dimensional vectors. Then, we use a measurement module with a bilayer architecture to establish the interaction between students and exercises, considering guessing and slipping factors. To capture long short-term dependencies on historical data, we design the long short-term learning transfer module based on the attention mechanism, which computes state transfer weights by incorporating occasion time and mastery state. Finally, extensive experimental results on four public datasets demonstrate the superiority and good interpretability of our proposed model.

Applying Predictive Analytics using Clickstream Data for Improving the Students Performance

Student performance analysis is an essential aspect of educational institutions. In recent years, machine learning (ML) has emerged as a promising tool to analyze student performance. To predict learning abilities of students and prescribing them a personalized learning curriculum, it is necessary to estimate their behavior to know about their weaknesses, strengths and help institutions to improve enrollment and retention. If it is possible for the teachers to predict in advance and prescribe ways to the at-risk and dropout students, they can plan more effectively to help them. We are describing in this paper various intelligent tutoring systems with Educational Data Mining, Predictive Learning Analytics, prediction of at-risk students at an earlier basis and how this prediction task is done. Predictive Analytics can also offer insights to help students to make informed decisions about each individual student to improve outcomes by understanding what drives each student behavior and how much the institution can create intensional, specific plans that will positively impact students.

For Educational Inclusiveness: Design and Implementation of an Intelligent Tutoring System for Student-Athletes Based on Self-Determination Theory

Student-athletes frequently struggle to strike a balance between their academic and athletic responsibilities. Various factors, such as age and competitive level, contribute to differences in their academic motivation and identity, showcasing the multifaceted needs they possess. While self-determination theory (SDT) has been proven effective for explaining student-athletes academic needs, its integration into learning design for this group remains limited. The developing AI technology, especially the Intelligent Tutoring System (ITS), offers the potential for creating personalized learning environments that can cater to the varying levels of motivation among student-athletes within the framework of SDT. Therefore, our paper explored how to build an SDT-based ITS for student-athletes to enhance their academic engagement and motivation. A two-stage experiment was conducted for: (a) identifying academic challenges faced by student-athletes in an online ITS; (b) evaluating the effectiveness of an SDT-based ITS design; and (c) exploring how autonomy, competence, and relatedness design affect their motivation. Results revealed that student-athletes face three challenges in learning in ITS: inflexible technology, identity missing, and mismatched learning difficulty. However, a significant improvement in academic engagement and motivation was shown when student-athletes faced an SDT-based ITS. In the meantime, the athletic motivation, which leads them to higher athletic performance, remains preserved and unaffected, showing a favorable outcome for student-athletes. This paper can provide practical implications for building a more inclusive and diverse learning environment for student-athletes.

Sim-GAIL: A generative adversarial imitation learning approach of student modelling for intelligent tutoring systems

The continuous application of artificial intelligence (AI) technologies in online education has led to significant progress, especially in the field of Intelligent Tutoring Systems (ITS), online courses and learning management systems (LMS). An important research direction of the field is to provide students with customised learning trajectories via student modelling. Previous studies have shown that customisation of learning trajectories could effectively improve students’ learning experiences and outcomes. However, training an ITS that can customise students’ learning trajectories suffers from cold-start, time-consumption, human labour-intensity, and cost problems. One feasible approach is to simulate real students’ behaviour trajectories through algorithms, to generate data that could be used to train the ITS. Nonetheless, implementing high-accuracy student modelling methods that effectively address these issues remains an ongoing challenge. Traditional simulation methods, in particular, encounter difficulties in ensuring the quality and diversity of the generated data, thereby limiting their capacity to provide intelligent tutoring systems (ITS) with high-fidelity and diverse training data. We thus propose Sim-GAIL, a novel student modelling method based on generative adversarial imitation learning (GAIL). To the best of our knowledge, it is the first method using GAIL to address the challenge of lacking training data, resulting from the issues mentioned above. We analyse and compare the performance of Sim-GAIL with two traditional Reinforcement Learning-based and Imitation Learning-based methods using action distribution evaluation, cumulative reward evaluation, and offline-policy evaluation. The experiments demonstrate that our method outperforms traditional ones on most metrics. Moreover, we apply our method to a domain plagued by the cold-start problem, knowledge tracing (KT), and the results show that our novel method could effectively improve the KT model’s prediction accuracy in a cold-start scenario.

On Using Conversational Frameworks to Support Natural Language Interaction in Intelligent Tutoring Systems

In this paper, we analyse the potential of conversational frameworks to support the adaptation of existing tutoring systems to a natural language form of interaction. We have based our research on a pilot study, in which the open-source machine learning framework Rasa has been used to build a conversational agent that interacts with an existing Intelligent Tutoring System (ITS) called Hypergraph Based Problem Solver (HBPS). This agent has been seamlessly integrated into the ITS to replace the previously available button-based user interface and allow the user to interact with HBPS in natural language. Once appropriately trained, the conversational agent was capable of identifying the intention of a given user utterance and extracting the relevant entities related to the message content, with average weighted F1-scores of 0.965 and 0.989 for intents and entities, respectively. Methodological guidelines are provided to generate a realistic training set that enables the creation of the required Natural Language Understanding (NLU) model and also evaluate the resulting system. These guidelines can be easily exported to other ITS and contexts, to provide an enhanced interaction based on natural language processing methods.

Recent Progress in the Use of Artificial Intelligence Tools in Education

The use of artificial intelligent (AI) tools in education has had a significant impact on learning experiences and outcomes. This review looks at recent advances in artificial intelligence tools and their implications for future research and practice. The review article followed the PRISMA method. Relevant articles on AI in education, specifically those describing the integration of AI or machine learning in undergraduate was extracted from the SCOPUS database. The inclusion criteria focus on articles directly related to teaching and training in structured programs that published in 2019 to 2023. A total of twelve documents were recognized and subjected to hand identification for subsequent analysis. The result shows that cognitive tutors, which are interactive learning environments facilitated by intelligent tutoring systems, improve learning outcomes. The challenge of balancing instructional assistance and self-directed learning, on the other hand, is inherent in AI-driven tools. AI tools in higher education provide numerous advantages at the institutional, social, and instructional levels. Disruptive AI tools such as ChatGPT have emerged, but challenges include job displacement concerns and the need for constant adaptation. AI language learning tools are important in language acquisition processes because they provide personalized learning paths and interactive engagement. However, ethical considerations and competencies related to AI-based tools in education are assessed, with parallels drawn to healthcare guidelines. It emphasizes the importance of strong ethical frameworks, as well as the critical role of educators and professionals in responsible AI use, in order to maintain a symbiotic relationship between human expertise and technological advancement. Overall, this review summarizes recent advances in the use of artificial intelligence tools to revolutionize education, emphasizing the importance of ongoing research, cross-disciplinary collaboration, and careful implementation.

Artificial intelligence in a modernizing science and technology education: a textual narrative synthesis in the COVID-19 era

The COVID-19 pandemic shifted the mode of learning to online. This gave the artificial intelligence (AI) developers the reason to increase its usage and production to every detail of the teaching learning process. This synthesis paper was intended to capture these new technologies in the last five years. Using the textual narrative analysis approach and course design triangle model, this paper looked into the AI integration in the field of science and technology education. A total of 15 studies were analyzed and synthesized coming from different journal hosting platforms such as Google Scholar, ERIC, Elsevier, etc. The results have shown that there is indeed a wider utilization of AI in various aspects of the teaching and learning process. These were seen in the learning activities, presentation translators, marking, feedbacking, predicting average score, and intelligent tutoring system. These AI technologies have proven to positively affect the learning of the students and helped the teachers along the process. Furthermore, there is a need to totally synthesize these AI systems which can be beneficial to a wider technical audience.

Revolutionizing Education: Artificial Intelligence's Pioneering Role in Shaping Tomorrow's Scholars

The integration of AI technologies into education represents a seismic shift, ushering in an era of personalized and adaptive learning experiences. Machine learning algorithms, with their ability to process vast amounts of data, enable the customization of educational content according to individual student needs. This tailored approach not only caters to diverse learning styles but also cultivates critical thinking, creativity, and problem-solving skills essential for the challenges of the 21st century. One of AI's significant contributions is its ability to create inclusive learning environments. Through speech recognition and natural language processing, AI ensures that education is accessible to all, breaking down barriers for students with disabilities and different learning abilities. Moreover, AI-driven applications facilitate real-time feedback, enhancing student-teacher interactions and fostering a collaborative learning atmosphere. Beyond the confines of traditional classrooms, AI enriches education through immersive technologies like virtual and augmented reality. These innovations transport students to historical events, scientific phenomena, and cultural landmarks, offering unparalleled learning experiences that stimulate curiosity and engagement. Intelligent tutoring systems, empowered by AI, provide interactive guidance, adapting to individual student progress and promoting self-directed learning. However, the integration of AI in education is not without its challenges. Ethical considerations, data privacy, and ensuring equitable access to technology demand careful attention. Collaborative efforts among educators, policymakers, and technologists are crucial to harnessing AI's full potential responsibly. In essence, "Empowering Tomorrow's Minds" paints a visionary picture of education where AI is not just a tool but a catalyst, nurturing a generation of lifelong learners equipped with the skills and knowledge to navigate an ever-changing world. Through thoughtful integration and collaborative endeavours, AI is shaping the evolution of education, empowering minds and paving the way for a brighter, more inclusive future.

Could the Technology for Adaptive Learning Systems Come out of GBL?

Games based learning (GBL) has a related field that it can draw upon: intelligent tutoring systems (ITS). Acommon concern in both fields is adaptivity, whereby the system can automatically adapt to the user. In order to supportthis adaptation, an ITS will generally include a user model and may also have a formal domain model. Work in this areastarted optimistically some years ago, but seems to have either lost some of that initial enthusiasm or been diverted intoother directions. We scan recent ITS literature to help consider why this might be, and suggest how GBL may be the fieldbest placed to take the work forward again. Learner models have long been seen as useful for adaptive learning systems.They include information about the learner which allows the system to adapt the course of learning materials andexercises to the learner's particular characteristics. In order to achieve a good quality of adaptation to the user, a detailedmodel of the required domain knowledge is typically added. The user and domain models then have to be broughttogether to lay out a course of exercises for the learner to do, and to track progress as the knowledge is learned. It's anattractive research programme, but recent work has moved to new issues, such as MOOCs. The reasons for that are partlyopportunistic and economical, but also suggest a deeper problem with the research programme. It is a costly task todevelop a domain model, and a suitable learner model that can take advantage of it. We suggest that GBL is in a goodposition to push through this cost barrier, because much of the effort is already implicitly involved in the game designprocess, which typically has to be more rigorously planned out in order to make the game a good one. One might thusexpect the next breakthroughs in adaptive learning systems to come from GBL. We further argue that the advantages toresearch, offered by the ITS framework, are also potentially beneficial to the way we teach the subject of GBL to ourstudents on game development courses.

Revolutionizing education: A study on Intelligent Tutoring Systems in U.S education

Over the decades, AI has been drastically impacting health care, entertainment, finance,transportation, and many other industries, but specifically, how has it impacted educationsystems in the United States? With a better ability at examining data points, strengths, andweaknesses, in this study, we investigate how MATHia, an intelligent tutoring system, usesAI and how it has affected student performance in mathematics. AI-driven online tutoringoffers a human-like learning environment that encourages collaboration with the students inorder to learn from them and create individualized courses based on the students' emotions,progress, and learning preferences. MATHia was developed to resemble a human tutor andpersonalize learning based on each individual's area of weakness. Did these online tutorspresent a cost-effective and revolutionary solution to real-life tutors? Was MATHia effectivein enhancing students' knowledge of the mathematical concepts they had to learn? What canbe done in the future to further expand the benefits of these systems? This research answersall of these questions by taking three standpoints into consideration (educational, economic,and futuristic standpoints), each with its own unique data, problems, and solutions to theseproblems.

Improving Knowledge Learning Through Modelling Students’ Practice-Based Cognitive Processes

Practice is an essential means by which humans and animals engage in cognitive activities. Intelligent tutoring systems, with a crucial component of modelling learners’ cognitive processes during learning and optimizing their learning strategies, offer an excellent platform to investigate students’ practice-based cognitive processes. In related studies, modelling methods for cognitive processes have demonstrated commendable performance. Furthermore, researchers have extended their investigations using decision-theoretic approaches, such as a partially observable Markov decision process (POMDP), to induce learning strategies by modelling the students’ cognitive processes. However, the existing research has primarily centered around the modelling of macro-level instructional behaviors rather than the specific practice selection made by the students within the intricate realms of cognitive domains. In this paper, we adapt the POMDP model to represent relations between the student’s performance on cognitive tasks and his/her cognitive states. By doing so, we can predict his/her performance while inducing learning strategies. More specifically, we focus on question selection during the student’s real-time learning activities in an intelligent tutoring system. To address the challenges on modelling complex cognitive domains, we exploit the question types to automate parameter learning and subsequently employ information entropy techniques to refine learning strategies in the POMDP. We conduct the experiments in two real-world knowledge concept learning domains. The experimental results show that the performance of the learning strategies induced by our new model is superior to that of other learning strategies. Moreover, the new model has good reliability in predicting the student’s performance. Utilizing an intelligent tutoring system as the research platform, this article addresses the modelling and strategy induction challenges of practice-based cognitive processes with intricate structures, aiming to tutor students effectively. Our work provides a new approach of predicting the students’ performance as well as personalizing their learning strategies.

Global and local neural cognitive modeling for student performance prediction

Student performance prediction is a critical task in supporting decision-making for Intelligent Tutoring Systems (ITS). Correct predictions of student performance are prerequisites for ITS to supply intelligent services and optimize learning efficiency, e.g., recommending the most appropriate learning resources for each student. Existing methods mainly include cognitive diagnosis and knowledge tracing, both of which focus on students’ cognitive modeling based on their interactions on a sequence of items and give predictions by assessing if their cognitive states can meet the item requirements. Specifically, cognitive diagnosis only considers students’ global static cognitive states, while knowledge tracing focuses on students’ local dynamics. However, both global and local features are critical for predicting student performance. Therefore, in this paper, we propose a novel Global and Local Neural Cognitive (GLNC) model to capture both global and local features in student-item interactions for more accurate predictions. Specifically, we first learn students’ global cognitive level according to all student-item interactions. Then, we propose a self-attentive encoder based on the scaled dot-product attention mechanism to extract the local cognitive dynamics and the dependencies between students’ recent interactions. Finally, to obtain better predictions, we design a fused gate based on the similarity between students’ recently responded items and the item to be predicted to adaptively combine the global and local features. To evaluate the effectiveness of GLNC, we compare it with both cognitive diagnosis and knowledge tracing methods. All experiments are conducted on three public datasets that contain real student-item interactions on mathematics or language courses from various ITS. The experimental results demonstrate that GLNC achieves an average score of 0.7810 on the AUC metric, 0.7627 on the ACC metric, 0.3987 on the RMSE metric, 0.2023 on the r2 metric, respectively achieving an average improvement of 1.84%, 1.07%, 1.87%, and 11.38% in contrast to existing state-of-the-art methods (i.e., NCD and LPKT). Moreover, we further analyze the performance of GLNC under different probabilities of guessing and slipping, the results indicate that GLNC is more robust against the influence of noisy data while considering both global and local features. Benefiting from the superior accuracy and stability, our proposed GLNC has a wide range of potential implications for ITS, which can be easily applied to improve students’ learning efficiency and experience.

Mapping Research Themes and Future Directions in Learning Style Detection Research: A Bibliometric and Content Analysis

This study aims to provide a comprehensive overview of the current state and potential future research in learning style detection. With the increasing number and diversity of research in this area, a quantitative approach is necessary to map out current themes and identify potential areas for future research. To achieve this goal, a bibliometric and content analysis will be conducted to map out the existing research and identify emerging topics and directions for future research. The study analyzes 1074 bibliographic sources from Scopus and visualizes the results of the bibliometric analysis through co-occurrence and thematic map analysis using VOSviewer and BibliometriX software. Content analysis is then conducted based on the results of the co-occurrence analysis. The findings reveal a significant increase in publications and citations in the field, with popular research topics including classification, adaptive learning, and MOOCs, and the most frequently used learning style models being Felder-Silverman, VARK, and Kolb. Emerging research topics include the use of EEG signals, online learning, and feature extraction. Future research may focus on classification, intelligent tutoring systems, MOOCs, online learning, adaptive learning, and deep learning. This study provides valuable insights into the current and future research trends in learning style detection, which can support the development of adaptive e-learning systems, intelligent tutoring systems, and MOOCs. By identifying popular research topics and emerging areas of study, this research can guide the design and implementation of effective online learning environments. Additionally, the study advances the field of e-learning knowledge by providing a comprehensive overview of the most frequently used learning style models and potential research areas. It sheds light on the ongoing development of learning style detection research and the potential for future advancements in the field, ultimately contributing to the growth and improvement of e-learning practices.

Predicting student disengagement: Harnessing visual cues for intelligent tutoring systems

Intelligent tutoring systems have the potential to enhance the learning experience for children, but it is crucial to detect and address early signs of disengagement to ensure effective learning. In this paper, we propose a method that utilizes visual features from a tablet tutor's user-facing camera to predict whether a student will complete the current activity or disengage from it. Unlike previous approaches that relied on tutor-specific features, our method leverages visual cues, making it applicable to various tutoring systems. We employ a deep learning approach based on a Long Short Term Memory (LSTM) model with a target replication loss function for prediction. Our model is trained and tested on screen capture videos of children using a tablet tutor for learning basic Swahili literacy and numeracy in Tanzania. With 40% of the activity remaining, our model achieves a balanced-class size prediction accuracy of 73.3%. Furthermore, we analyze the variation in prediction accuracy across different tutor activities, revealing two distinct causes of disengagement. The findings indicate that our model can not only predict disengagement but also identify visual indicators of negative affective states that may not lead to non-completion of the task. This work contributes to the automated detection of early signs of disengagement, which can aid in improving tutoring systems and guiding pedagogical decisions in real-time.

Artificial intelligence technologies and applications for language learning and teaching

Abstract Artificial intelligence (AI) is changing many aspects of education and is gradually being introduced to language education. This article reviews the literature to examine main trends and common findings in relation to AI technologies and applications for second and foreign language learning and teaching. With special reference to computer-assisted language learning (CALL), the article explores natural language processing (NLP), data-driven learning (DDL), automated writing evaluation (AWE), computerized dynamic assessment (CDA), intelligent tutoring systems (ITSs), automatic speech recognition (ASR), and chatbots. It contributes to discussions on understanding and using AI-supported language learning and teaching. It suggests that AI will be continuously integrated into language education and AI technologies and applications will have a profound impact on language learning and teaching. Language educators need to ensure that AI is effectively used to support language learning and teaching in AI-powered contexts. More rigorous research on AI-supported language learning and teaching is recommended to maximise second and foreign language learning and teaching with AI.

An architecture for the dynamic adaptation of an intelligent multi-tutoring system

The articulation between machine tutoring and human tutoring remains a productive research within in the context of Intelligent Tutoring Systems (ITS), particularly in the context of e-learning where the dropout rate is high. We explore an innovative approach, the automation of tutoring as it is done in the classroom to respond to the difficulties of the learner. We propose a generic Intelligent Multi-Tutoring System (IMTS) architecture composed of two modules COMES and MAT. The Communication Entry Service (COMES) module manages communications between the IMTS and a Learning Management System (LMS). The module Multi-Agent Tutoring (MAT) is the multi-agent system developed with JADE, which allows the dynamic adaptation of tutoring (Machine, Peer, Teacher) according to the profile of the learner. We offer a configurable system to customize tutoring to the individual needs of each learner. It can be grafted onto any learning platform, making it multidisciplinary and easy to integrate into existing learning environments. The teacher will be able to devote more time to learners which need greater his intervention.The peer will develop human and relational qualities linked to their know-how, transversal skills sought by recruiters. To validate this architecture, we provide an application and results that integrate the elements of the described model. The results of the experiment prove the feasibility and reliability of our approach.

Impact of Engaging with Intelligent Tutoring System Lessons Prior to Class Start

A study was conducted using the Generalized Intelligent Framework for Tutoring (GIFT) intelligent tutoring system (ITS) software and an Army Schoolhouse course. Existing materials were provided and used to create 9 computer-based GIFT lessons that included adaptive tutoring versions of the materials. These lessons included a Pre-Test, 7 content lessons (on the areas of Detect, Engage, and Assess), and a Post-Test. Six participants completed the Pre-Test, Post-Test, and all lessons. Overall Post-Test scores were significantly higher than Pre-Test scores, and remediation also had a positive impact on Post-Test scores. This study demonstrates that completing self-paced ITS lessons prior to initial class instruction can lead to positive learning impacts prior to the start of a class.