Showing papers on "Intelligent tutoring system published in 2020"
01 May 2020
TL;DR: This work proposes a methodology using genetic algorithms for the optimization of hyperparameters of a CNN, used to identify the affective state of a person, and presents the optimized network embedded into an intelligent tutoring system running on a mobile phone.
Abstract: An intelligent tutoring system is used as an efficient self-learning tutor, where decisions are based on the affective state of the user. These detected emotions are what experts call basic emotions and the best-known recognition technique is the recognition of facial expressions. A convolutional neural network (CNN) can be used to identify emotions through facial gestures with very high precision. One problem with convolutional networks, however, is the high number of hyperparameters to define, which can range from a hundred to a thousand. This problem is usually solved by an expert experience combined with trial and error optimization. In this work, we propose a methodology using genetic algorithms for the optimization of hyperparameters of a CNN, used to identify the affective state of a person. In addition, we present the optimized network embedded into an intelligent tutoring system running on a mobile phone. The training process of the CNN was carried out on a PC with a GPU and the trained neural network was embedded into a mobile environment. The results show an improvement of 8% (from 74 to 82%) with genetic algorithms compared to a previous work that utilized a trial and error method.
41 citations
TL;DR: Assessing the relation of dual gaze, tutor log, audio and dialog data to students' learning gains, it is found that a combination of modalities provides a more accurate prediction of learning gains than models with a single modality.
Abstract: The analysis of multiple data streams is a long-standing practice within educational research. Both multimodal data analysis and temporal analysis have been applied successfully, but in the area of collaborative learning, very few studies have investigated specific advantages of multiple modalities versus a single modality, especially combined with temporal analysis. In this paper, we investigate how both the use of multimodal data and moving from averages and counts to temporal aspects in a collaborative setting provides a better prediction of learning gains. To address these questions, we analyze multimodal data collected from 25 9?11-year-old dyads using a fractions intelligent tutoring system. Assessing the relation of dual gaze, tutor log, audio and dialog data to students' learning gains, we find that a combination of modalities, especially those at a smaller time scale, such as gaze and audio, provides a more accurate prediction of learning gains than models with a single modality. Our work contributes to the understanding of how analyzing multimodal data in temporal manner provides additional information around the collaborative learning process.
35 citations
TL;DR: In this article, a bibliometric analysis was conducted to obtain an overview of its trends from publication outputs, countries' cooperation, cluster analysis, and research evolution, and three prospective directions for future EAI research were suggested.
Abstract: Educational artificial intelligence (EAI) refers to the use of artificial intelligence (AI) to support personalized and automated feedback and guidance in the educational field. Inevitably, it serves as a more important part of the educational system in the coming years. However, novel development in this field has been inadequately reviewed and conceptualized in a visualized, objective and comprehensive way. In this view, a bibliometric analysis was conducted to obtain an overview of its trends from publication outputs, countries’ cooperation, cluster analysis, and research evolution. Around 8660 Scopus-published articles from 2000 to 2019 were gathered for analysis using CiteSpace and Alluvial generator. In the study, a growing interest in EAI research and deepening cooperation among countries was first identified, entailing favorable conditions for promoting globalization in this aspect. Afterward, five core clusters were established for the intellectual structure of EAI, including intelligent tutoring system, learning system, student, labeled training data, and pedagogy. The development of EAI research was further conceptualized as follows: (a) technological foundation; (b) technological breakthrough; (c) intelligent application; and (d) symbiotic integration. Finally, three prospective directions for future EAI research were suggested.
34 citations
TL;DR: According to results, the systems were designed for a wide range of fields such as Information Technologies, Mathematics, Science, Medicine, and Foreign Language Education and content adaptation was generally used in these systems.
Abstract: The aim of this study is to examine adaptation elements and Intelligent Tutoring System (ITS) elements used in Adaptive Intelligent Tutoring Systems (AITSs), using meta-synthesis methods to analyze the results of previous research. Toward this end, articles appearing in the Web of Science, Google Scholar, Eric and Science Direct databases in 2000 and later were identified with the keyphrase “adaptive intelligent tutoring system.” Application of exclusion and inclusion procedures to the articles accessed in the search resulted in the selection of 32 articles, which were analyzed using meta-synthesis methods and then evaluated in the light of prespecified themes and elements used in AITSs were determined. According to results, the systems were designed for a wide range of fields such as Information Technologies, Mathematics, Science, Medicine, and Foreign Language Education. In these systems, content adaptation was generally used, based mostly on such criteria as feedback, student level, student learning and cognitive styles, and student performance. And besides 4 basic ITS modules (knowledge, student, teaching and user interface), some different modules such as guide module, strategy module, personal learning module, knowledge base module, communication module, system administrator module and messaging module were used. Finally, some suggestions were given for such studies in the future.
34 citations
TL;DR: Results indicated that including NLP indices and machine learning increased accuracy by more than 10% as compared to classic readability metrics, demonstrating the importance of considering deeper features of language related to text difficulty as well as the potential utility of hierarchical machine learning approaches in the development of meaningful text difficulty classification.
Abstract: For decades, educators have relied on readability metrics that tend to oversimplify dimensions of text difficulty This study examines the potential of applying advanced artificial intelligence methods to the educational problem of assessing text difficulty The combination of hierarchical machine learning and natural language processing (NLP) is leveraged to predict the difficulty of practice texts used in a reading comprehension intelligent tutoring system, iSTART Human raters estimated the text difficulty level of 262 texts across two text sets (Set A and Set B) in the iSTART library NLP tools were used to identify linguistic features predictive of text difficulty and these indices were submitted to both flat and hierarchical machine learning algorithms Results indicated that including NLP indices and machine learning increased accuracy by more than 10% as compared to classic readability metrics (eg, Flesch-Kincaid Grade Level) Further, hierarchical outperformed non-hierarchical (flat) machine learning classification for Set B (72%) and the combined set A + B (65%), whereas the non-hierarchical approach performed slightly better than the hierarchical approach for Set A (79%) These findings demonstrate the importance of considering deeper features of language related to text difficulty as well as the potential utility of hierarchical machine learning approaches in the development of meaningful text difficulty classification
28 citations
21 Jun 2020
TL;DR: An interactive, tablet-based learning platform with a multi-step math task designed using Common Core State Standards shows that embedding learning activities into narratives boosted children's engagement as evaluated by coding video responses and surveys, and the integration of a tutoring chatbot improved learning outcomes on the assessment.
Abstract: A key challenge in education is effectively engaging children in learning activities We investigated how a narrative story impacts engagement and learning, as well as how feedback can provide further benefits To do so, we created an interactive, tablet-based learning platform with a multi-step math task designed using Common Core State Standards Subjects completed a pretest and then were assigned to a condition, either one of three variations of the system (narratives, narratives with hints, and narratives with a tutoring chatbot using wizard-of-oz techniques) or a control system that has children complete the same learning task without narratives nor feedback, before the subjects completed a post test 72 children in US grades 3--5 participated Our results showed that embedding learning activities into narratives boosted children's engagement as evaluated by coding video responses and surveys, and the integration of a tutoring chatbot improved learning outcomes on the assessment These results provide evidence that a narrative-based tutoring system with chatbot-mediated help may support effective learning experiences for children
22 citations
26 Aug 2020
TL;DR: Sherlock as discussed by the authors is a tutoring system for the US Air Force that provides advice at both the circuit path and individual component level of investigation, with student-initiated coaching on the most difficult parts of the task.
Abstract: The Sherlock story began about a decade ago when our research and development team responded to the US Air Force’s need for an efficient training technology. Budget cutbacks across the armed services, as well as a shrinking pool of enlisted soldiers prompted the Air Force to look to Intelligent Tutoring Systems as a tool for training avionics technicians expediently in the skills needed to do their jobs, namely, diagnosing faults in, and repairing, faulty aircraft and the systems used to maintain them. Perhaps most importantly, the student can ask for advice at any point while troubleshooting. Sherlock provides advice at both the circuit path and individual component levels of investigation. The design of Sherlock 2 was also driven by the principles of apprenticeship learning upon which its predecessor, Sherlock, was based, that is, modeling of expert troubleshooting behavior, student-initiated coaching on the most difficult parts of the task, gradual fading of support as expertise is acquired.
19 citations
TL;DR: A crucial finding from the study is that ATS can be a promising tutoring system for the next generation learning environment by affiliating proper emotion recognition channels, along with computational intelligence approaches.
Abstract: The swelling use of computerized learning, accompanied by the rapid growth of information technology has become a surge of interest in the research community. Consequently, several technologies have been developed to maintain and promote computerized learning. In this study, we provided an in-depth analysis of two of the prominent computerized learning systems i.e., Intelligent Tutoring System (ITS) and Affective Tutoring System (ATS). An ITS is one of the training software systems, which use intelligent technologies to provide personalized learning content to students based on their learning needs with the aim of enhancing the individualized learning experience. Recently, researchers have demonstrated that the affect or emotional states of a student have an impact on the overall performance of his/her learning, which introduces a new trend of ITS development termed as ATS, which is the extended research of the previous one. Although there have been several studies on these tutoring systems, however, none of them has comprehensively analyzed both systems, particularly the transition from ITS to ATS. Therefore, this study examines these two tutoring systems more inclusively with regards to their architectures, models, and techniques and approaches used by taking into consideration the related researches conducted between 2014 to 2019. A crucial finding from the study is that ATS can be a promising tutoring system for the next generation learning environment by affiliating proper emotion recognition channels, along with computational intelligence approaches. Finally, this study concludes with research challenges and possible future directions and trends.
18 citations
TL;DR: The effects of teaching the text structure strategy using a web-based Intelligent Tutoring System for the Text Structure Strategy (ITSS) were examined with fourth- and fifth-grade children scoring below the 25th percentile on comprehension measures using the Gray Silent Reading Test and researcher designed assessment.
Abstract: The effects of teaching the text structure strategy using a web-based Intelligent Tutoring System for the Text Structure Strategy (ITSS) were examined with fourth- and fifth-grade children scoring below the 25th percentile on comprehension measures using the Gray Silent Reading Test (GSRT) and researcher designed assessment from 130 fourth-grade and 130 fifth-grade classrooms. The ITSS was designed to teach students how to select and encode strategic memory from expository texts. The system provides modelling, practice, assessment, scaffolding, and feedback to learners on identifying signalling words, summarizing, making inferences, generating elaborations, and monitoring comprehension. A large scale randomized controlled trial was conducted with 130 fourth-grade and 130 fifth-grade classrooms. Students completed GSRT- and researcher-designed measures of reading comprehension at pretest and posttests. An analysis of fourth-grade students using ITSS who scores less than the 25th percentile on the GSRT pretest showed small but meaningful effect sized on the posttests. The fifth-grade students in ITSS, who scored less than the 25% percentile on the GSRT pretest, showed the highest effect sizes (moderate to large effects) on the standardized test scores on the posttests.
17 citations
TL;DR: An improved knowledge base supporting adaptive learning is presented, which can be achieved by a suitable knowledge construction, which provides adaptive presentation and personalized learning with the proposed adaptive algorithm.
17 citations
06 Jul 2020
TL;DR: The authors proposed a machine learning approach to generate personalized feedback, which takes individual needs of students into account, and demonstrated that the personalized feedback leads to considerable improvement in student learning outcomes and in the subjective evaluation of the feedback.
Abstract: We investigate how automated, data-driven, personalized feedback in a large-scale intelligent tutoring system (ITS) improves student learning outcomes. We propose a machine learning approach to generate personalized feedback, which takes individual needs of students into account. We utilize state-of-the-art machine learning and natural language processing techniques to provide the students with personalized hints, Wikipedia-based explanations, and mathematical hints. Our model is used in Korbit (https://www.korbit.ai), a large-scale dialogue-based ITS with thousands of students launched in 2019, and we demonstrate that the personalized feedback leads to considerable improvement in student learning outcomes and in the subjective evaluation of the feedback.
TL;DR: The review of previous researches and in-depth analysis of several studies have proved that an intelligent tutoring system has made a positive impact on personalized learning, bringing some visible contributions in enhancing the performance of students and providing better time management.
Abstract: With the advancements of technological solutions and the changes in human society has brought personalized learning into the limelight. A major technological solution has stream rolled personalized learning around the world in the development and advancements of Intelligent tutoring systems. The review of previous researches and in-depth analysis of several studies have proved that an intelligent tutoring system has made a positive impact on personalized learning, bringing some visible contributions in enhancing the performance of students and providing better time management. This research explores and unveils what personalized learning is all about and the role of an intelligent tutoring system in personalized learning. The work also covers how intelligent tutoring system has enhanced the performance of students, reduced cost for training institutes and educational system. The data in this research was collected through several means ranging from Internet research, one-on-one interviews, observations, and Educational Focus groups. Through the research methods, theoretical and empirical data were gathered. For interviews, data was effectively analyzed using content analysis techniques. The research work concludes with acknowledgment of the effects of intelligent tutoring system on personalized learning.
TL;DR: The idea of clustering students according to their online learning behavior has the potential to provide more than more-more-more Adaptive adaptive- Adaptive-Scaffolding-style learning, says KEywoRDS.
Abstract: The idea of clustering students according to their online learning behavior has the potential of providing more adaptive scaffolding by the intelligent tutoring system itself or by a human teacher. With the aim of identifying student groups who would benefit from the same intervention in ACware Tutor, this research examined online learning behavior using 8 tracking variables: the total number of content pages seen in the learning process; the total number of concepts; the total online score; the total time spent online; the total number of logins; the stereotype after the initial test, the final stereotype, and the mean stereotype variability. The previous measures were used in a four-step analysis that consisted of data preprocessing, dimensionality reduction, the clustering, and the analysis of a posttest performance on a content proficiency exam. The results were also used to construct the decision tree in order to get a human-readable description of student clusters. KEywoRDS Blended Learning, Clustering, Decision Tree, Educational Data Mining, Flipped Classroom, Intelligent Tutoring System, Online Learning Behavior, Principal Component Analysis
TL;DR: In this article, the authors examined implementation models and dosage levels for a supplemental software, and investigated adherence to the core components of the software and extent to which the supplement enabled personalized instruction.
Abstract: Evidence is emerging that technology-based curricula and adaptive learning systems can personalize students' learning experiences and facilitate development of mathematical skills. Yet, evidence of efficacy in rigorous studies for these blended instructional models is mixed. These studies highlight challenges implementing the systems in classrooms, which may contribute to a lack of consistently positive effects on student learning. This article extends the literature by closely examining implementation models and dosage levels for a supplemental software, two gaps in existing research. It also investigates adherence to the core components of the software, and extent to which the supplement enabled personalized instruction. The study was conducted in 40 algebra I classes in an urban school district. Sixty-two percent of classes implemented models that integrated instructional modalities. There was mixed adherence to core components of the software in classes that used it. In the vast majority of classes (94%), software did not enable personalized instruction. Software and the existing curricula were largely independent and did not inform each other. Only one class implemented an integrated instructional model, adhered to the core design components of the software, and demonstrated high levels of personalized instruction. Findings identify implementation barriers and offer suggestions for future implementations and studies of technology-enabled personalization.
TL;DR: The proposal of this work focuses on offering an ITS that can be applied in programming learning environments with the objective of introducing programming transversally in different application areas and offering a complementary mechanism that facilitates its learning.
Abstract: The learning of programming is a field of research with relevant studies and publications for more than 25 years. Since its inception, it has been shown that its difficulty lies in the high level of abstraction required to understand certain programming concepts. However, this level can be reduced by using tools and graphic representations that motivate students and facilitate their understanding, associating real-world elements with specific programming concepts. Thus, this paper proposes the use of an intelligent tutoring system (ITS) that helps during the learning of programming by using a notation based on a metaphor of roads and traffic signs represented by 3D graphics in an augmented reality (AR) environment. These graphic visualizations can be generated automatically from the source code of the programs thanks to the modular and scalable design of the system. Students can use them by leveraging the available feedback system, and teachers can also use them in order to explain programming concepts during the classes. This work highlights the flexibility and extensibility of the proposal through its application in different use cases that we have selected as examples to show how the system could be exploited in a multitude of real learning scenarios.
TL;DR: It could be concluded that the new system contributed in terms of the speed of performing the final exam and high academic success and the time taken to perform the post-test indicated that students who use the FB-ITS needed less time on average compared to students who used the traditional e-learning system.
Abstract: In this experimental study, an intelligent tutoring system called the fuzzy Bayesian intelligent tutoring system (FB-ITS), is developed by using artificial intelligence methods based on fuzzy logic and the Bayesian network technique to adaptively support students in learning environments. The effectiveness of the FB-ITS was evaluated by comparing it with two other versions of an Intelligent Tutoring System (ITS), fuzzy ITS and Bayesian ITS, separately. Moreover, it was evaluated by comparing it with an existing traditional e-learning system. In order to evaluate whether the academic performance of the students in different learning groups differs or not, analysis of covariance (ANCOVA) was used based on the students’ pre-test and post-test scores. The study was conducted with 120 undergraduate university students. Results showed that students who studied using FB-ITS had significantly higher academic performance on average compared to other students who studied with the other systems. Regarding the time taken to perform the post-test, the results indicated that students who used the FB-ITS needed less time on average compared to students who used the traditional e-learning system. From the results, it could be concluded that the new system contributed in terms of the speed of performing the final exam and high academic success.
TL;DR: This paper describes the lessons learned during the iterative development process of a short, intensive course in algebraic model construction, which combines human teaching with a tutoring system.
Abstract: An algebraic model uses a set of algebra equations to precisely describe a situation. Constructing such models is a fundamental skill required by US standards for both math and science. It is usually taught with algebra word problems. However, many students still lack the skill, even after taking several algebra courses in high school and college. We are developing a short, intensive course in algebraic model construction. The course combines human teaching with a tutoring system. This paper describes the lessons learned during the iterative development process. Starting from an existing theory of model construction, we gradually acquired a completely different view of the skills required as we modified the tutoring system and the instruction. We close by describing encouraging results from a quasi-experimental study.
21 Apr 2020
TL;DR: An intelligent tutoring system for sketching fundamentals called Sketchtivity is designed and developed, and deployed in to six existing courses at the high school and university level during the 2017-2018 school year.
Abstract: Sketching is a practical and useful skill that can benefit communication and problem solving. However, it remains a difficult skill to learn because of low confidence and motivation among students and limited availability for instruction and personalized feedback among teachers. There is an need to improve the educational experience for both groups, and we hypothesized that integrating technology could provide a variety of benefits. We designed and developed an intelligent tutoring system for sketching fundamentals called Sketchtivity, and deployed it in to six existing courses at the high school and university level during the 2017-2018 school year. 268 students used the tool and produced more than 116,000 sketches of basic primitives. We conducted semi-structured interviews with the six teachers who implemented the software, as well as nine students from a course where the tool was used extensively. Using grounded theory, we found ten categories which unveiled the benefits and limitations of integrating an intelligent tutoring system for sketching fundamentals in to existing pedagogy.
TL;DR: Using the students’ interaction logs with AmritaITS to predict student performance, in English and Mathematics subjects, via summative and formative assessments, and predict students who may be at risk of failing the final examination, demonstrated promise in identifying students who might be atrisk of suffering from reading difficulties.
Abstract: In many rural Indian schools, English is a second language for teachers and students. Intelligent tutoring systems have good potential because they enable students to learn at their own pace, in an exploratory manner. This paper describes a 3-year longitudinal study of 2123 Indian students who used the intelligent tutoring system, AmritaITS. The aim of the study was to use the students’ interaction logs with AmritaITS to: (1) predict student performance, in English and Mathematics subjects, via summative and formative assessments, (2) predict students who may be at risk of failing the final examination and (3) screen students who may have reading difficulties. The prediction models for summative assessments were significantly improved by formative assessments scores, along with AmritaITS logs. The receiver operating characteristic (ROC) curve showed that students at risk of failing a class could be identified early, with high sensitivity and specificity. The models also provide recommendations for the amount of time required for students to use the system, and reach the appropriate grade level. Finally, the models demonstrated promise in identifying students who might be at risk of suffering from reading difficulties.
01 Jan 2020
TL;DR: This article extends the literature by closely examining implementation models and dosage levels for a supplemental software, two gaps in existing research, and investigates adherence to the core components of the software, and extent to which the supplement enabled personalized instruction.
Abstract: Evidence is emerging that technology-based curricula and adaptive learning systems can personalize students' learning experiences and facilitate development of mathematical skills. Yet, evidence of efficacy in rigorous studies for these blended instructional models is mixed. These studies highlight challenges implementing the systems in classrooms, which may contribute to a lack of consistently positive effects on student learning. This article extends the literature by closely examining implementation models and dosage levels for a supplemental software, two gaps in existing research. It also investigates adherence to the core components of the software, and extent to which the supplement enabled personalized instruction. The study was conducted in 40 algebra I classes in an urban school district. Sixty-two percent of classes implemented models that integrated instructional modalities. There was mixed adherence to core components of the software in classes that used it. In the vast majority of classes (94%), software did not enable personalized instruction. Software and the existing curricula were largely independent and did not inform each other. Only one class implemented an integrated instructional model, adhered to the core design components of the software, and demonstrated high levels of personalized instruction. Findings identify implementation barriers and offer suggestions for future implementations and studies of technology-enabled personalization.
08 Jun 2020
TL;DR: Assessment of the amount and quality of research conducted to design and develop ITSs for training psychomotor abilities and the developed tutors use ITS architectures or variations, and capture several sub-fields of the psychom motor domain.
Abstract: Intelligent Tutoring Systems (ITSs) were proven efficient for supporting cognitive tasks; however, their potential contribution to support the development of other human skills is less known, even though they could be of high relevance in dealing with health issues. Lack of physical activity is considered the fourth leading cause for preventable death worldwide. Thus, our current work is aimed at assessing the amount and quality of research conducted to design and develop ITSs for training psychomotor abilities. A systemic literature search was conducted on the most reputable online data sources. After methodological filtering, a short-list of these studies was analyzed in-depth, and the results of their efficacy were considered through a structured comparative grid. The developed tutors use ITS architectures or variations, and capture several sub-fields of the psychomotor domain, from medicine (e.g., surgery, radiology), to military (e.g., training marksmanship), or learning to drive.
06 Jul 2020
TL;DR: Although Korbit was designed to be open-domain and highly scalable, A/B testing experiments with real-world students demonstrate that both student learning outcomes and student motivation are substantially improved compared to typical online courses.
Abstract: We present Korbit, a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system (ITS). Korbit uses machine learning, natural language processing and reinforcement learning to provide interactive, personalized learning online. Korbit has been designed to easily scale to thousands of subjects, by automating, standardizing and simplifying the content creation process. Unlike other ITS, a teacher can develop new learning modules for Korbit in a matter of hours. To facilitate learning across a wide range of STEM subjects, Korbit uses a mixed-interface, which includes videos, interactive dialogue-based exercises, question-answering, conceptual diagrams, mathematical exercises and gamification elements. Korbit has been built to scale to millions of students, by utilizing a state-of-the-art cloud-based micro-service architecture. Korbit launched its first course in 2019 and has over 7, 000 students have enrolled. Although Korbit was designed to be open-domain and highly scalable, A/B testing experiments with real-world students demonstrate that both student learning outcomes and student motivation are substantially improved compared to typical online courses.
Posted Content•
TL;DR: This work proposes a machine learning approach to generate personalized feedback, which takes individual needs of students into account, and utilizes state-of-the-art machine learning and natural language processing techniques to provide the students with personalized hints, Wikipedia-based explanations, and mathematical hints.
Abstract: We investigate how automated, data-driven, personalized feedback in a large-scale intelligent tutoring system (ITS) improves student learning outcomes. We propose a machine learning approach to generate personalized feedback, which takes individual needs of students into account. We utilize state-of-the-art machine learning and natural language processing techniques to provide the students with personalized hints, Wikipedia-based explanations, and mathematical hints. Our model is used in Korbit, a large-scale dialogue-based ITS with thousands of students launched in 2019, and we demonstrate that the personalized feedback leads to considerable improvement in student learning outcomes and in the subjective evaluation of the feedback.
07 Jul 2020
TL;DR: Overall the results showed that the HRL induced policies could significantly improve students' learning performance, and explaining the tutor's decisions to students through data-driven explanations could improve the student-system interaction in terms of students' engagement and autonomy.
Abstract: Motivated by the recent advances of reinforcement learning and the traditional grounded Self Determination Theory (SDT), we explored the impact of hierarchical reinforcement learning (HRL) induced pedagogical policies and data-driven explanations of the HRL-induced policies on student experience in an Intelligent Tutoring System (ITS). We explored their impacts first independently and then jointly. Overall our results showed that 1) the HRL induced policies could significantly improve students' learning performance, and 2) explaining the tutor's decisions to students through data-driven explanations could improve the student-system interaction in terms of students' engagement and autonomy.
TL;DR: An architecture to build an intelligent chatbot, which can tutor to solve problems, and construct scripts for automatically tutoring is designed and the experimental results show the effectiveness of the proposed method in comparison with the existing systems.
Abstract: Nowadays, intelligent systems have been applied in many real-word domains. The Intelligent chatbot is an intelligent system, it can interact with the human to tutor how to work some activities. In this work, we design an architecture to build an intelligent chatbot, which can tutor to solve problems, and construct scripts for automatically tutoring. The knowledge base of the intelligent tutoring chatbot is designed by using the requirements of an Intelligent Problem Solver. It is the combination between the knowledge model of relations and operators, and the structures of hint questions and sample problems, which are practical cases. Based on the knowledge base and tutoring scripts, a tutoring engine is designed. The tutoring chatbot plays as an instructor for solving real-world problems. It simulates the working of the instructor to tutor the user for solving problems. By utilizing the knowledge base and reasoning, the architecture of the intelligent chatbot are emerging to apply in the real-world. It is used to build an intelligent chatbot to support the learning of high-school mathematics and a consultant system in public administration. The experimental results show the effectiveness of the proposed method in comparison with the existing systems.
TL;DR: The obtained results indicate that the application of hybrid technology in ITSs is feasible because, for defining the teaching strategies, it incorporates the teacher’s knowledge and by neural network use, it assimilates the students’ learning process behavior.
Abstract: This paper presents an intelligent tutoring system (ITS) model that is capable of driving the didactic transposition of contents. Initially, the tutoring system reactions bases its behavior on rules defined by an expert teacher; after this, a neural network that learns from the student’s behavior when they are studying adjusts these rules. This way, the neural network improves the teacher’s rules and, consequently, defines a learning strategy that is more adaptive and reactive to the student’s profile. Thus, it is possible to offer the student a personalized and individualized education form. The model is able to guide the student throughout the didactic transposition of contents, aiding the consolidation of desired competencies established on educational propositions. This work shows the development process of the ITS, including the expert guidance system and the hybrid system, which improves the expert rules from SOM neural network use. The obtained results indicate that the application of hybrid technology in ITSs is feasible because, for defining the teaching strategies, it incorporates the teacher’s knowledge and by neural network use, it assimilates the students’ learning process behavior. The results show that proposed model has great agreement between the actions of the “ITS” and the students’ actions. The model showed satisfactory performance when compared to other systems proposed in the literature that use connectionist approach in its conception.
01 Jan 2020
TL;DR: This chapter provides a brief description of the intelligent tutoring system, current developments, instructional techniques, proposed solution, and future recommendations to provide insights on self-regulated learning.
Abstract: With digitization, a rapid growth is seen in educational technology. Different formal and informal learning contents are available on the internet. Intelligent tutoring system provides personalized e-learning to the learners. Different attributes like historical data, real-time data, behavioral, and cognitive are usually used for personalization. Based on the personalization, the intelligent tutoring system aims to provide easy and effective understanding. Recent research highlights the effect of learner's behavior and emotions on effective teaching-learning process. This chapter provides a brief description of the intelligent tutoring system, current developments, instructional techniques, proposed solution, and future recommendations. The emphasis of the study is to provide insights on self-regulated learning.
TL;DR: An intelligent tutoring system for learning basic statistics, called Stat-Knowlab, is presented and analyzed and it is highlighted that the system is useful for monitoring the student learning processes during a university course of basic statistics.
Abstract: An intelligent tutoring system for learning basic statistics, called Stat-Knowlab, is presented and analyzed. The algorithms implemented in the system are based on the competence-based knowledge space theory, a mathematical theory developed for the formative assessment of knowledge and learning. The system’s architecture consists of the two assessment and learning modules that interact with each other in a continuous exchange of information about the current knowledge state of a student. This allows the system to personalize the student’s learning, providing only with the learning objects that she is ready to learn. During the browsing of the system, several types of navigation data are recorded. In this work, we analyzed data from two studies that were aimed at examining the learning processes induced by the navigation of the system. The results of both studies highlighted that the system is useful for monitoring the student learning processes during a university course of basic statistics.
TL;DR: This method, as an intelligent tutoring system, could be used in a wide range of applications from online learning environments and e-learning, to learning and remembering techniques in traditional methods such as adjusting delayed matching to sample and spaced retrieval training that can be used for people with memory problems such as people with dementia.
Abstract: An adaptive task difficulty assignment method which we reckon as balanced difficulty task finder (BDTF) is proposed in this paper. The aim is to recommend tasks to a learner using a trade-off between skills of the learner and difficulty of the tasks such that the learner experiences a state of flow during the learning. Flow is a mental state that psychologists refer to when someone is completely immersed in an activity. Flow state is a multidisciplinary field of research and has been studied not only in psychology, but also neuroscience, education, sport, and games. The idea behind this paper is to try to achieve a flow state in a similar way as Elo's chess skill rating (Glickman in Am Chess J 3:59-102) and TrueSkill (Herbrich et al. in Advances in neural information processing systems, 2006) for matching game players, where "matched players" should possess similar capabilities and skills in order to maintain the level of motivation and involvement in the game. The BDTF draws analogy between choosing an appropriate opponent or appropriate game level and automatically choosing an appropriate difficulty level of a learning task. This method, as an intelligent tutoring system, could be used in a wide range of applications from online learning environments and e-learning, to learning and remembering techniques in traditional methods such as adjusting delayed matching to sample and spaced retrieval training that can be used for people with memory problems such as people with dementia.
19 Aug 2020
TL;DR: In this paper, a computerized adaptive test (CAT) based on IRT (Item Response Theory) stepwise estimates every examinee' response to every question item and provides the examinee with the next corresponding and appropriate question item.
Abstract: On the contrary to classical school test, the computerized adaptive test (CAT) based on IRT (Item Response Theory) stepwise estimates every examinee’ response to every question item and provides the examinee with the next corresponding and appropriate question item. The online intelligent tutoring system “Lexue 100” has been used by more than 100,000 junior high school students in China in the past 7 years. It has more than 70,000 sets of mathematics quizzes designed for different units in the various textbooks. Each of about 68,600 quizzes among the 70,000 sets has been used by more than 100 students. We analyzed those quizzes, calibrated the original 740,910 IRT parameters for the questions composing the quizzes, recalculated the parameters by using linking algorithms for 194,205 question items. Based on this large question bank with pre-calibrated parameters for every question, we designed and implemented a computerized adaptive test system for school mathematics.