Meta-learning Process Analytics for Adaptive Tutoring Systems

2020 ◽  
pp. 411-423
Author(s):  
Gracja Niesler ◽  
Andrzej Niesler
Keyword(s):  
Learning Process ◽  
Tutoring Systems ◽  
Process Analytics ◽  
Meta Learning ◽  
Adaptive Tutoring

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.

Neuro-adaptive tutoring systems - Neurophysiological-based recognition of affective-emotional and cognitive states of learners for intelligent neuro-adaptive tutoring systems

2021 ◽  
pp. 243-260
Author(s):  
Katharina Lingelbach ◽  
◽  
Sabrina Gado ◽  
Wilhelm Bauer
Keyword(s):  
Brain Activity ◽  
Learning Experience ◽  
Intelligent Tutoring System ◽  
Training Session ◽  
Mental States ◽  
Machine Learning Algorithms ◽  
Tutoring Systems ◽  
Cognitive States ◽  
Oscillatory Power ◽  
Adaptive Tutoring

Monitoring learners’ mental states via a passive Brain-Computer Interface (BCI) allows to continuously estimate current abilities, available cognitive resources, and motivation. It bears the great potential to adapt educational contents, learning speed, and format to the learner’s needs via an intelligent tutoring system. We present a neurophysiological-based approach to continuously monitor learners’ current affective-emotional and cognitive states by measuring and decoding brain activity via a passive BCI. In two studies (N = 8 and N = 7), we investigate whether we can a) predict learners’ affective and cognitive states during a learning or training session, b) provide continuous feedback of recognized states to the learner and, thereby, c) increase performance and intrinsic motivation. Oscillatory power measures in the alpha (8 – 12 Hz) and theta (4 – 7 Hz) frequency band served as features for the prediction and visualization. Our results reveal that machine learning algorithms can distinguish different states of cognitive workload and affect. The approach contributes to the development of closed-loop neuro-adaptive tutoring systems which allow to monitor learners’ states, provide feedback, and adapt their parameters for an optimal learner-training fit and effective and positive learning experience.

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.

Meta Learning and the AI Learning Process

2021 ◽  
pp. 1-15
Author(s):  
Samyakh Tukra ◽  
Niklas Lidströmer ◽  
Hutan Ashrafian
Keyword(s):  
Learning Process ◽  
Meta Learning

Modeling of Adaptive Tutoring Processes

2006 ◽  
pp. 193-215 ◽  
Author(s):  
Alke Martens
Keyword(s):  
Teaching And Learning ◽  
Process Model ◽  
Learning Strategy ◽  
Learning Material ◽  
Formal Approach ◽  
Tutoring Systems ◽  
Reusable Components ◽  
Case Based Learning ◽  
Adaptive Tutoring ◽  
Case Based

In this chapter, a formal, adaptive tutoring process model for case-based Intelligent Tutoring Systems (ITSs) is described. Combining methods of Artificial Intelligence and Cognitive Science led to the development of ITSs more than 30 years ago. In contrast to the common agreement about the ITSs’ architecture, components of ITSs are rarely reusable. Reusability in ITSs is intimately connected with the application domain, that is, with the contents that should be learned and with the teaching and learning strategy. An example of a learning strategy is case-based learning, where the adaptation of the learning material to the learner plays a major role. Adaptation should take place automatically at runtime, and thus should be part of the ITS’s functionality. To support the development of ITSs with reusable components and the communication about and the evaluation of similar ITSs, a formal approach has been chosen. This approach is called the tutoring process model.

Authoring Adaptive Tutoring Systems for Complex Visual Skills

2009 ◽  
Author(s):  
Alexandre Direne ◽  
Luis Bona ◽  
Marcos Sfair Sunye ◽  
Marcos Castilho ◽  
Fabiano Silva ◽  
...  
Keyword(s):  
Tutoring Systems ◽  
Visual Skills ◽  
Adaptive Tutoring
Sign in / Sign up

Export Citation Format

Share Document