Adaptation to Learners' Learning Styles in a Multi-Agent E-Learning System

<p><strong><em>Abstract—A </em></strong><strong>learning style is an issue related to learners. In one way or the other, learning styles could assist learners in their learning activities. If the learners ignore their learning styles, it may influence their effort in understanding teaching materials. To overcome these problems, a model for reliable automatic learning style detection is needed. Currently, there are two approaches in automatically detecting learning styles: data driven and literature based. Learners, especially those with changing learning styles, have difficulties in adopting these two approaches since they are not adaptive, dynamic and responsive (ADR). To solve the above problems, a model using agent learning approach is proposed. Agent learning performs four phased activities, i.e. initialization, learning, matching and recommendations to decide which learning styles are used by the students. Furthermore, the system will provide teaching materials which are appropriate for the detected learning style. The detection process is performed automatically by combining data-driven and literature-based approaches. The detected learning style used for this research is VARK (Visual, Auditory, Read/Write, and Kinesthetic). This learning style detection model is expected to optimize the learners in adhering with the online learning.</strong><strong></strong></p>

Each learner has their own preferences in the learning process. Differences in preferences are closely related to the learning style of each learner. Personalization of e-learning is an overview of online learning that has been customized content based on learning styles of each learner. Detecting learning style needs a technique that is effective and accurate. This study combines literature based method with Support Vector Machine (SVM) to detect students' learning styles. The data used is learning log data of Data Structures and Algorithms class at the Faculty of Computer Science, Universitas Indonesia. The test results showed that SVM has better accuracy compared to Naive Bayes.

The intelligent agent paradigm has generated such a remarkable interest in many application domains over the last two decades. It is growing to be a continuously evolving and expanding area. Agents, Software Agents or Intelligent Agents are intelligent in the sense that they are adaptive, independent, and possess reasoning capability. They can plan and execute tasks in cooperation with other agents in order to satisfy their goals. A MultiAgent System (MAS) is defined as a loosely coupled network of problem solvers that work together to solve problems that are beyond the individual capabilities or knowledge of each problem solver (Agent). The increasing interest in MAS research is due to significant advantages inherent in such systems, including their ability to solve problems that may be too large for a centralized single agent, provide enhanced speed and reliability, and tolerate uncertain data and knowledge. Some of the key research issues related to problem-solving activities of agents in a multi-agent system MAS are in the areas of coordination, negotiation, and communication. With advances in Web technologies, collaborative applications are now server based and the user interface is typically a Web browser. Thus, a collaborative application can be a Webbased solution that runs on a local server that allows people communicate and work together, share information and documents, and talk in real-time over the Internet. Recently, much research has been conducted in distributed artificial intelligence and collaborative applications. Several interesting methodologies and systems have been developed in areas such as distributed multi-agent systems for decision support, web search and information retrieval, information systems modeling, and supply chain management. This chapter considers applying different data mining techniques for the decision making process in a Multi-Agent System for Collaborative E-learning (MASCE). The dynamism in elearning can be made more powerful with the help of intelligent agents. Intelligent agents – the so called e-assistants or helper programs can reside inside a computer and make the learning in e-learning occur dynamically to suit the need of the user. They can track the user’s likes and dislikes in different areas, the level of knowledge and the learning style and accordingly recommend the best matching helpers for collaboration. A previous research outlined the development and the implementation processes of a MultiAgent System for Collaborative E-learning (MASCE) which is designed to be used to assist

The goal of this paper is to develop a system, referred to as the Management System for Merging Learning Objects (msMLO), which offers an approach that retrieves learning objects (LOs) based on students’ learning styles and term-based queries and produces a new outcome. The first step ranks LOs using a unified learning style model and creates better LOs by merging the top-ranked LOs. The second step maps LOs onto a hierarchy of concepts to avoid including duplicated topics in the merged LO. Fifty-six students were randomly split into experimental and control groups. The experimental group browsed the LOs retrieved by the msMLO based on the students’ learning styles, term-based queries and merge functionality, whereas the control group browsed the LOs retrieved based on the students’ learning styles and term-based queries. The results demonstrated that the experimental group improves their learning performance, thus msMLO is a promising approach.

The ability to detect learners’ learning styles based on their learning behaviors is of utmost importance for online educational systems, as it greatly enhances student engagement, motivation, and overall learning outcomes. Knowing the learning preferences of learners may significantly aid in creating personalized learning recommendations and empower learners to identify their own learning styles. However, learners exhibit diverse behaviors in an online setting, which poses significant difficulties in detecting their learning style. This paper proposes a novel approach for detecting learning styles using graph representation learning techniques and machine learning algorithms. While our approach is not reliant on a particular learning style model, our approach may be divided into two distinct parts. Initially, we represented the behavior of learners as a bipartite graph and then transformed this graph into a lower-dimensional representation using the graph embedding approach. This lower-dimensional representation was then utilized for machine learning tasks. Furthermore, we categorize the encoded learner’s sequence using a clustering technique based on the selected learning style model. Our methodology uses the Felder-Silverman model as the learning style model and the Fuzzy C-means algorithm as a clustering technique. Our approach was evaluated using the 2015 KDD Cup dataset through a series of comprehensive experiments to showcase its effectiveness. The findings demonstrate that our approach surpasses the previous approach, achieving an average precision of 0.8737 and an accuracy of 0.9182.

A student’s learning style is the approach for learning that best allows the student to gather and to understand knowledge in a specific manner. Providing students with learning materials and activities that fit to their learning styles seems to have high potential to make learning easier for them. This research aims at providing teachers with recommendations on how to best extend their existing e-courses in learning management systems to accommodate more students with different learning styles. A smart e-course recommender tool has been developed for this purpose, which analyzes the e-courses with respect to their support levels for different students’ learning styles, recommends learning objects to be added to the courses, and visualizes the recommendations and the improvement in the course support level for students’ with different learning styles. The experimental results indicate that the tool has the ability to recommend suitable learning objects that, once being added, significantly improve the course support level for accommodating more students with different learning styles.

Learning style is an important factor that accounts for the individual student learning in any learning environment. Every student has a different learning style and different ways to percept, process, retain and understand new information. In this paper, a new approach is proposed to classify students learning style automatically and dynamically depending on their learning behavior in a learning management system (LMS). There have been several approaches proposed for automatic learning style detection. One of the widely accepted and frequently used classification techniques is the decision tree classifier. The decision tree classifier mainly depends on the construction of strong decision rules which are required to identify learning styles accurately. The lack of strong decision rules would lead to the misclassification of individual students learning style. Hence, this paper mainly focuses on the construction of strong decision rules to strengthen the existing decision tree classifier to accurately and precisely classify students learning style thereby improving the classification accuracy. The proposed approach has experimented with an average of 300 students enrolled for the online courses in Moodle LMS. Initially, the students' behavior are extracted from the web log files of LMS and then preprocessed to build decision tree classifier using strong decision rules based on the three learning dimensions of standard Felder Silverman learning style model (FSLSM). The evaluation result is obtained using the inference engine with forward reasoning searches of the rules until the correct learning style is determined. Based on the result obtained, the prediction of learning style is done for the new students automatically and accurately using the significant rules built in the decision tree classifier. The experimental result proved that the processing dimension shows variance in classification whereas perception and input dimension shows less variance with an average accuracy of 87%.

The purpose of this study is to describe students' mathematical communication skills in Problem Based Learning viewed from students' learning styles. The type of research used is qualitative research supported by observation data, questionnaires and interviews. Validity testing is the credibility test, transferability, dependability, and confirmability. The results of the study indicate that students' mathematical communication skills viewed from learning styles include visual learning styles (30.4%), auditory (34.8%), and kinesthetic (26.1%) and visual-kinesthetic (8.7%). Mathematical ability indicators on a scale of 0-10 include 1) The ability to express ideas orally, in writing and demonstrate them and describe them visually (8.78), 2) The ability to understand, interpret, and evaluate mathematical ideas orally, in writing and demonstrate them and describe them visually (8.21), 3) The ability to use mathematical terms, notations, and their structures to present ideas describing relationships with situation models (5.30). The appropriate learning style is the key to student success in learning. The use of learning styles that are limited to only one form can cause an imbalance in absorbing information. Therefore, in learning activities, students need to be helped and directed to recognize the learning style that suits them so that learning objectives can be achieved effectively.

Video games are increasingly becoming more intelligent, able to adapt themselves to the individual gamer. Learning styles are a set of models used to categorize people into different types of learners to explain why some people learn better through different methods. Since learning and exploration are such fundamental parts of the video game experience, it is interesting to consider the possibility of applying these learning style models to video games, allowing the video game to adapt to its player, providing a better experience. To consider such adaptation, the game must first be able to detect that learning style from how the player has interacted with it. Simple metrics collected during game play of an instrumented game (opensource Supertux) are compared to the results of the Hay Group’s Kolb Learning Style Inventory, a paper test designed to determine one’s learning style. A relationship between recordable game play metrics and the academic model for learning would allow a game designer to potentially infer that model from game play and use it to adapt the game to that type of learner.

Higher education models appear to be not entirely designed to support students in facing severe challenges, such as failure in exams and dropping out of school. To solve these challenges, several models of learning styles have been proposed, under the premise that these studies contribute to improving the student's learning experience. This research aims at quantifying the impact of learning styles (learning preferences/dimensions) on students' academic performance from a higher education institution. Ninety-six undergraduate students were surveyed during the 2018-2019 school year and randomly divided into two groups: control (CG) and experimental (EG). The learning preferences of the students were identified using the Unified Learning Style Model (ULSM) instrument. Subsequently, the level of students’ knowledge concerning the course was determined employing a pre-test exam. As a following step, the students of the EG consulted the learning objects designed considering different learning styles. The CG attend their lessons in a face-to-face environment; both groups answered a post-test exam to assess their learning. The learning styles' effect -learning objects were designed to cover several learning styles- on academic performance is quantified employing an ANOVA analysis. The results differ from those postulated in previous researches based on the ULSM since there is no statistical evidence that learning styles influence students' academic performance. Therefore, it is necessary to explore other cognitive and affective factors that make the student's learning experience efficient and effective.

The paper aims to suggest a method of using artificial neural for learning personalisation. Learning personalisation consists form learning style identification then linking it to learning activities and objects which correspond to learning style. But the problem is that learning style identified by questionnaire cannot guarantee adequacy and objectivity. In order to overcome this issue we can use artificial neural network which could analyse learner in learning activities and interactionwith learning objects and correct learning style and scenarios characteristics according to collected information.

Intelligent learning systems provide relevant learning materials to students based on their individual pedagogical needs and preferences. However, providing personalized learning objects based on learners’ preferences, such as learning styles which are particularly important for the recommendation of learning objects, re-mains a challenge. Recommending the most appropriate learning objects for learners has always been a challenge in the field of e-learning. This challenge has driven educators and researchers to implement new ideas to help learners improve their learning experience and knowledge. New solutions use artificial intelligence (AI) techniques such as machine learning (ML) and natural language processing (NLP). In this paper, we propose and develop a new personalization approach for recommendation that implements the adaptation of learning objects according to the learners’ learning style mainly focused on the use of a chatbot, named LearningPartnerBot, which will be integrated into the Moodle platform. We use the Felder-Silverman Learning Styles Model to determine learners’ learning styles in order to recommend learning objects, and also to overcome the cold start problem. A chatbot is an automated communication tool that attempts to imitate a conversation by detecting the intentions of its user. The proposed LearningPartnerBot should be able to answer learners’ questions in real time and provide a relevant set of suggestions according to their needs.

One of the most important features of adaptative e-learning systems is the personalisation according to specific requirements of each individual student. In considering learning and how to improve student learning, these systems must know the way in which an individual learns. In this context, we introduce a new approach for consistent evolution of student models by automatic detection of student learning styles. Most of the work in this field presents complex and inefficient approachs. Our approach is based on learning styles combination and dynamic correction of inconsistencies in the student model, taking into account the non-deterministic aspect of the learning process. Promising results were obtained from tests, and some of them are discussed in this paper.

The wide use of e-technologies represents a great opportunity for underserved segments of the population, especially with the aim of reintegrating excluded individuals back into society through education. This is particularly true for people with different types of disabilities who may have difficulties while attending traditional on-site learning programs that are typically based on printed learning resources. The creation and provision of accessible e-learning contents may therefore become a key factor in enabling people with different access needs to enjoy quality learning experiences and services. Another e-learning challenge is represented by m-learning (which stands for mobile learning), which is emerging as a consequence of mobile terminals diffusion and provides the opportunity to browse didactical materials everywhere, outside places that are traditionally devoted to education. Both such situations share the need to access materials in limited conditions and collide with the growing use of rich media in didactical contents, which are designed to be enjoyed without any restriction. Nowadays, Web-based teaching makes great use of multimedia technologies, ranging from Flash animations to prerecorded video-lectures. Rich media in e-learning can offer significant potential in enhancing the learning environment, through helping to increase access to education, enhance the learning experience and support multiple learning styles. Moreover, they can often be used to improve the structure of Web-based courses. These highly variegated and structured contents may significantly improve the quality and the effectiveness of educational activities for learners. For example, rich media contents allow us to describe complex concepts and process flows. Audio and video elements may be utilized to add a “human touch” to distance-learning courses. Finally, real lectures may be recorded and distributed to integrate or enrich on line materials. A confirmation of the advantages of these approaches can be seen in the exponential growth of video-lecture availability on the net, due to the ease of recording and delivering activities which take place in a traditional classroom. Furthermore, the wide use of assistive technologies for learners with disabilities injects new life into e-learning systems. E-learning allows distance and flexible educational activities, thus helping disabled learners to access resources which would otherwise present significant barriers for them. For instance, students with visual impairments have difficulties in reading traditional visual materials, deaf learners have trouble in following traditional (spoken) lectures, people with motion disabilities have problems in attending on-site programs. As already mentioned, the use of wireless technologies and pervasive computing may really enhance the educational learner experience by offering mobile e-learning services that can be accessed by handheld devices. This new paradigm of educational content distribution maximizes the benefits for learners since it enables users to overcome constraints imposed by the surrounding environment. While certainly helpful for users without disabilities, we believe that the use of newmobile technologies may also become a fundamental tool for impaired learners, since it frees them from sitting in front of a PC. In this way, educational activities can be enjoyed by all the users, without hindrance, thus increasing the social inclusion of non-typical learners. While the provision of fully accessible and portable video-lectures may be extremely useful for students, it is widely recognized that structuring and managing rich media contents for mobile learning services are complex and expensive tasks. Indeed, major difficulties originate from the basic need to provide a textual equivalent for each media resource composing a rich media Learning Object (LO). Moreover, tests need to be carried out to establish whether a given LO is fully accessible to all kinds of learners. Unfortunately, both these tasks are truly time-consuming processes, depending on the type of contents the teacher is writing and on the authoring tool he/she is using. Due to these difficulties, online LOs are often distributed as partially accessible or totally inaccessible content. Bearing this in mind, this thesis aims to discuss the key issues of a system we have developed to deliver accessible, customized or nomadic learning experiences to learners with different access needs and skills. To reduce the risk of excluding users with particular access capabilities, our system exploits Learning Objects (LOs) which are dynamically adapted and transcoded based on the specific needs of non-typical users and on the barriers that they can encounter in the environment. The basic idea is to dynamically adapt contents, by selecting them from a set of media resources packaged in SCORM-compliant LOs and stored in a self-adapting format. The system schedules and orchestrates a set of transcoding processes based on specific learner needs, so as to produce a customized LO that can be fully enjoyed by any (impaired or mobile) student.

Various types of learners can be observed in today’s e-learning environments. Learning Analytics can offer insights on a student’s actions and behaviour. We can correlate this data with the identification of learning styles like in the Felder-Silverman Learning Styles Model (FSLSM), and use it for user modelling. Supported by visualizations on learning styles and learning behaviour students and instructors can reflect the learning process. Based on our previously published conceptual model for linking learning analytics and learning styles in e-learning environments, we present an Integrated Learning Styles Analytics system (ILSA), which supports identification of learning styles as well as analysis and visualization of activity data in the Moodle LMS. ILSA consists of a questionnaire for learning style identification derived from FSLSM and offers immediate results to its participants. Next, by utilizing various data sources in Moodle, e.g. log data or the grade book, we are able to correlate a user’s activity with their learning styles. This work offers details on the finalized concept as well as its implementation. By providing insights on data sources in Moodle and presenting various visualizations, this work allows teachers to reuse the system in their e-learning courses.