scholarly journals Enhancing the Effectiveness of Intelligent Tutoring Systems Using Adaptation and Cognitive Diagnosis Modeling

2021 ◽  
Author(s):  
Akrivi Krouska ◽  
Christos Troussas ◽  
Filippos Giannakas ◽  
Cleo Sgouropoulou ◽  
Ioannis Voyiatzis
Keyword(s):  
Student Engagement ◽  
Student Performance ◽  
Learning Process ◽  
Intelligent Tutoring ◽  
Learning Goals ◽  
Diagnostic Model ◽  
Knowledge Level ◽  
Tutoring Systems ◽  
Learning Path ◽  
Improving Student Performance

This paper presents a novel framework for developing educational hypermedia systems incorporating adaptation techniques and tailored feedback. In particular, the adaptation techniques refers to the content presentation; where the system hides/displays information according to students’ knowledge level and learning goals, and to the navigation design; where the system proposes the learning path that is better to be followed based on their profile. Finally, the framework embodies a diagnostic model that analyzes the students’ misconceptions and provides tailored feedback and advices on bridging students’ knowledge gap. This framework aims to enhance the effectiveness of learning process, increasing student engagement through the adaptive content and navigation and improving student performance through the tailored feedback.

scholarly journals Automated Data-Driven Generation of Personalized Pedagogical Interventions in Intelligent Tutoring Systems

2021 ◽  
Author(s):  
Ekaterina Kochmar ◽  
Dung Do Vu ◽  
Robert Belfer ◽  
Varun Gupta ◽  
Iulian Vlad Serban ◽  
...  
Keyword(s):  
Machine Learning ◽  
Student Performance ◽  
Language Processing ◽  
Intelligent Tutoring Systems ◽  
Large Scale ◽  
Intelligent Tutoring ◽  
Performance Outcomes ◽  
Data Driven ◽  
Personalized Feedback ◽  
Tutoring Systems

AbstractIntelligent tutoring systems (ITS) have been shown to be highly effective at promoting learning as compared to other computer-based instructional approaches. However, many ITS rely heavily on expert design and hand-crafted rules. This makes them difficult to build and transfer across domains and limits their potential efficacy. In this paper, we investigate how feedback in a large-scale ITS can be automatically generated in a data-driven way, and more specifically how personalization of feedback can lead to improvements in student performance outcomes. First, in this paper we propose a machine learning approach to generate personalized feedback in an automated way, which takes individual needs of students into account, while alleviating the need of expert intervention and design of hand-crafted rules. We leverage state-of-the-art machine learning and natural language processing techniques to provide students with personalized feedback using hints and Wikipedia-based explanations. Second, we demonstrate that personalized feedback leads to improved success rates at solving exercises in practice: our personalized feedback model is used in , a large-scale dialogue-based ITS with around 20,000 students launched in 2019. We present the results of experiments with students and show that the automated, data-driven, personalized feedback leads to a significant overall improvement of 22.95% in student performance outcomes and substantial improvements in the subjective evaluation of the feedback.

Recent Advances in Intelligent Tutoring Systems

2013 ◽  
pp. 631-647
Author(s):  
Joel J. P. C. Rodrigues ◽  
Pedro F. N. João ◽  
Isabel de la Torre Díez
Keyword(s):  
Learning Process ◽  
Intelligent Tutoring Systems ◽  
Intelligent Tutoring ◽  
Field Tests ◽  
Study Guide ◽  
Web Based ◽  
Tutoring Systems ◽  
Recent Advances ◽  
The Web

Intelligent Tutoring Systems (ITS) include interactive applications with some intelligence that supports the learning process. Some of ITS have had a very large impact on educational outcomes in field tests, and they have provided an important ground for artificial intelligence research. This chapter elaborates on recent advances in ITS and includes a case study presenting an ITS called EduTutor. This system was created for the Web-Based Aulanet Learning Management System (LMS). It focuses on subjects for the first cycle of studies of the Portuguese primary education system, between the first and the fourth year. It facilitates the perception of the learning process of each student, individually, in a virtual environment, as a study guide. Moreover, EduTutor has been designed and its architecture prepared for being easily integrated into higher levels of studies, different subjects, and several languages. Currently, it is used in the Aulanet LMS platform.

A Perspective Projection Tutoring System With Motivation Diagnosis and Planning

2007 ◽  
Author(s):  
Yong Se Kim ◽  
Hyun Jin Cha ◽  
Tae Bok Yoon ◽  
Jee-Hyoung Lee
Keyword(s):  
Fuzzy Logic ◽  
Student Success ◽  
Learning Process ◽  
Intelligent Tutoring Systems ◽  
Multiagent System ◽  
Emotional State ◽  
Intelligent Tutoring ◽  
Perspective Projection ◽  
Tutoring System ◽  
Tutoring Systems

Motivation is a paramount factor to student success. Although it is well known that the learner’s motivation and emotional state in educational contexts are very important, they have not been fully addressed in intelligent tutoring systems (ITS). In this paper, a method for integrated motivation diagnosis and motivational planning is described in a manner applied to an operable system. For the motivational diagnosis rules, three different channels of data (performance from interaction with the system, verbal communication, and feedbacks) are combined. For the motivational planning rules, four different strategies (different learning process, helps, different teaching strategies, and arousal questions or feedbacks) are combined. By applying the mechanisms, a tutoring system for the topic of perspective projection with motivation diagnosis and motivational planning on a multiagent system with fuzzy logic has been implemented.

Developing Adaptive and Intelligent Tutoring Systems (AITS)

2014 ◽  
Vol 10 (4) ◽  
pp. 70-85
Author(s):  
Mohamed Hafidi ◽  
Tahar Bensebaa
Keyword(s):  
Multiple Intelligences ◽  
Learning Style ◽  
Learning Process ◽  
Intelligent Tutoring Systems ◽  
Intelligent Tutoring ◽  
Skill Level ◽  
Learning Performance ◽  
Difficulty Level ◽  
Tutoring Systems ◽  
The Individual

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 Comparison of Three Learning Strategies in Intelligent Tutoring Systems

1996 ◽  
Vol 14 (4) ◽  
pp. 371-383 ◽  
Author(s):  
Claude Frasson ◽  
Esma Aimeur
Keyword(s):  
Knowledge Acquisition ◽  
Learning Strategies ◽  
Learning Process ◽  
Intelligent Tutoring Systems ◽  
Learning Strategy ◽  
Intelligent Tutoring ◽  
Tutoring Systems ◽  
New Approaches ◽  
Self Confidence ◽  
New Learning

New approaches in Intelligent Tutoring Systems imply a more active participation of the learner in the learning process. The motivation of the learner can be increased by interaction with a companion who strengthens the knowledge acquisition in a cooperation climate. In this article we introduce a new learning strategy called learning by disturbing intended to improve student self-confidence. We compare it to directive learning and peer learning, discussing the advantage and the inconvenience of each one. We present some experiments realized to show in which condition a strategy can be useful or not. We analyze and discuss results obtained.

scholarly journals Multi-Relational and Social-Influence Model for Predicting Student Performance in Intelligent Tutoring Systems (ITS)

2020 ◽  
Vol 9 (3) ◽  
pp. 2058-2066
Keyword(s):  
Student Performance ◽  
Performance Prediction ◽  
Matrix Factorization ◽  
Intelligent Tutoring Systems ◽  
Mean Squared Error ◽  
Mutual Influence ◽  
Intelligent Tutoring ◽  
Essential Elements ◽  
Tutoring Systems ◽  
Predicting Student Performance

Recent studies have shown that Matrix Factorization (MF) method, deriving from recommendation systems, can predict student performance as part of Intelligent Tutoring Systems (ITS). In order to improve the accuracy of this method, we hypothesize that taking into account the mutual influence effect in the relations of student groups would be a major asset. This criterion, coupled with those of the different relationships between the students, the tasks and the skills, would thus be essential elements for a better performance prediction in order to make personalized recommendations in the ITS. This paper proposes an approach for Predicting Student Performance (PSP) that integrates not only friendship relationships such as workgroup relationships, but also mutual influence values into the Weighted Multi-Relational Matrix Factorization method. By applying the Root Mean Squared Error (RMSE) metric to our model, experimental results from KDD Challenge 2010 database show that this approach allows to refine student performance prediction accuracy.

EduTutor

2010 ◽  
Vol 8 (4) ◽  
pp. 66-80 ◽  
Author(s):  
Joel J.P.C. Rodrigues ◽  
Pedro F. N. João ◽  
Binod Vaidya
Keyword(s):  
Learning Process ◽  
Intelligent Tutoring ◽  
Intelligent Tutoring System ◽  
Large Set ◽  
Web Based ◽  
Tutoring Systems ◽  
Tutor System ◽  
Intelligent Tutor System ◽  
Teaching Learning ◽  
Intelligent Tutor

Intelligent tutoring systems are any computer systems encompassing interactive applications with some intelligence that support and facilitate the teaching-learning process. The intelligence of these systems is the ability to adapt to each student throughout his/her learning process. This paper presents an intelligent tutoring system, called EduTutor, created for the web-based Aulanet learning management system (LMS).The system architecture and its main characteristics are described in detail. EduTutor focuses on subjects for the first cycle of studies of the Portuguese primary education system, between the first and the fourth year. Its purpose is to facilitate the perception of the learning process of each student, individually, in a virtual environment, and as a study guide. Furthermore, this intelligent tutor system was designed and its architecture was prepared for being easily integrated in higher levels of studies, different subjects, and different languages. EduTutor was validated with a large set of real cases and is being used, with success, in the Aulanet LMS platform.

scholarly journals The choice of customisation strategies in training: An overview of parameters and their systematisation

2021 ◽  
pp. 170-186
Author(s):  
Marina Anikieva
Keyword(s):  
Learning Process ◽  
Learning System ◽  
Learning Goals ◽  
Individual Student ◽  
Educational Strategies ◽  
Learning Materials ◽  
Educational Activities ◽  
Learning Path ◽  
Large Numbers ◽  
E Learning

This paper discusses the factors that determine the customisation of e-learning programmes. The process of customisation depends on many parameters, such as the objectives of the programme, the quantity and order of the learning materials, the personality and abilities of the student, and the resources within the learning system. Curriculum developers are able to put together these parameters in varying combinations, reflecting differing educational strategies. Because of this possibility it has become important to study how one can determine an appropriate strategy or learning path for any individual student. This is becoming particularly relevant because curriculum developers have to consider large numbers of already developed learning courses, modules, and technologies. One of the approaches to addressing this problem is the classification, or taxonomy, of customisation parameters. This paper reviews published material from highly-rated journals dealing with customisation of learning. As a result of this review the groups of customisation parameters are identified and a generalised scheme of grouped parameters, and their sequence, corresponding to the inner logic of the learning process are developed. This taxonomy allows the educational activities to be arranged so that learners can achieve their learning goals more efficiently.

Sign in / Sign up

Export Citation Format

Share Document