Search

Artificial intelligence (AI) has seen rapid advancements, establishing itself as a robust tool for fostering accessible teaching and learning environments. Nevertheless, the efficacy of these intelligent learning settings in bolstering the engagement and learning outcomes for students with hearing impairments warrants further investigation. This research leveraged Design-Based Research (DBR) to iteratively refine intelligent learning environments, while also adopting the Community of Inquiry (COI) and Technology Acceptance Model (TAM) to assess classroom presence and perception among students with hearing impairments. The results revealed notable enhancements in teaching presence, cognitive presence, social presence, and overall perception within intelligent learning contexts for hearing-impaired students. Additionally, their understanding of abstract and ill-structured knowledge significantly improved. Such findings offer valuable insights for the design of inclusive teaching and learning environments in special education. [ABSTRACT FROM AUTHOR]

This work seeks to contribute to the development of intelligent environments by presenting an approach oriented to the identification of On-Task and Off-Task behaviors in educational settings. This is accomplished by monitoring and analyzing the user-object interactions that users manifest while performing academic activities with a tangible-intangible hybrid system in a university intelligent environment configuration. With the proposal of a framework and the Orange Data Mining tool and the Neural Network, Random Forest, Naive Bayes, and Tree classification models, training and testing was carried out with the user-object interaction records of the 13 students (11 for training and two for testing) to identify representative sequences of behavior from user-object interaction records. The two models that had the best results, despite the small number of data, were the Neural Network and Naive Bayes. Although a more significant amount of data is necessary to perform a classification adequately, the process allowed exemplifying this process so that it can later be fully incorporated into an intelligent educational system. [ABSTRACT FROM AUTHOR]

This article presents a survival analysis-based model to estimate the duration of the emotion of confusion in students during learning. Academic confusion can have both positive and negative effects, and its persistence can lead to negative emotions. The model considers crucial factors such as personality traits and students' prior knowledge, which have been shown to significantly influence the duration of confusion. To investigate this relationship, data were collected from seventh-grade students who used an intelligent tutoring system to solve algebra problems. The results of the analysis of data from 25 students revealed statistically significant differences in the duration of confusion based on different personality traits and prior algebra knowledge. Additionally, a model of intervention for intelligent learning environments was proposed when students are confused, based on the developed model. This module determines the optimal time to intervene and provide individualized assistance tailored to the student's knowledge for the specific problem. The study contributes to understanding the dynamics of academic confusion and highlights the importance of considering emotions and their duration, as well as personality traits and prior knowledge, when designing appropriate interventions in intelligent learning environments. Identifying the opportune moment to intervene when a student is confused is essential to promote a more effective learning process, allowing educators to adopt personalized approaches to meet individual students' needs and facilitate their learning journey. [ABSTRACT FROM AUTHOR]

It is well known that learners using intelligent learning environments make different use of the feedback provided by the intelligent learning environment and exhibit different patterns of behaviour. Traditional approaches to measuring such behaviour have focused on observational methods, think-aloud protocols, ratings and log data. More recently, the field of educational neuroscience has placed greater emphasis on real-time measures using eye tracking, electroencephalogram and functional magnetic resonance imaging. Our work fits into the latter vein. Drawing on a literature review from cognitive psychology, neuroscience and education, we describe our Learner Processing of Feedback in Intelligent Learning Environments model of how learners process feedback. We also present findings from a pilot study as a preliminary test of the model. Seventeen learners participated in an experiment using the intelligent learning environment known as Crystal Island. A range of data was collected, including a pre-test measuring prior knowledge, think-alouds, log data, video recordings, biometrics and post-task questionnaires. We discuss these findings and steps forward to further validate the model using physiological measures. [ABSTRACT FROM AUTHOR]

In e-learning environments, tutors perform the main function of tutoring. They follow up learners and answer their assistance requests which require different skills. These requests may not belong to the tutors' skills and competencies, so collaboration among other tutors is expected. In fact, this collaboration can improve tutors' skills and provide learners with effective monitoring. It can be permanent and adaptive, according to learners' needs and requests. Grouping tutors with different skills is the aim of this research. In this paper, a new technique for grouping tutors is presented. The proposed technique is called K-complementarity. It is based on the complementarity of roles that are assigned to tutors. K-complementarity is based on tutor model and aims at obtaining K groups of tutors who have the most of the roles and skills. The proposed technique has been used by a Computer-Supported Collaborative Tutoring (CSCTT) system. This system had been tested in an Algerian University. The obtained results showed that the groups' members are heterogeneous and the groups are homogeneous. Furthermore, each group had more than 80% of the roles by combining those of its members. So, these results can be considered as acceptable and very encouraging. [ABSTRACT FROM AUTHOR]

• Creation of two dataset for emotions and sentiments in text. • Recognitions of learning-centered emotions in text. • Comparison among machine & deep learning methods against an evolutionary approach. • Integration of best classification model to an intelligent learning environment. This paper presents a comparison among several sentiment analysis classifiers using three different techniques – machine learning, deep learning, and an evolutionary approach called EvoMSA – for the classification of educational opinions in an Intelligent Learning Environment called ILE-Java. To make this comparison, we develop two corpora of expressions into the programming languages domain, which reflect the emotional state of students regarding teachers, exams, homework, and academic projects, among others. A corpus called sentiTEXT has polarity (positive and negative) labels, while a corpus called eduSERE has positive and negative learning-centered emotions (engaged, excited, bored, and frustrated) labels. From the experiments carried out with the three techniques, we conclude that the evolutionary algorithm (EvoMSA) generated the best results with an accuracy of 93% for the corpus sentiTEXT, and 84% for the corpus eduSERE. [ABSTRACT FROM AUTHOR]