A Fuzzy C-means Algorithm to Detect Learning Styles in Online Learning Environment

<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>

Learning style detection is essential for developing adaptive learning tailored to learner preferences. Extensive research has been conducted to address the limitations of direct learner engagement, behavioral-based approaches, and the lack of learner-teacher interaction caused by the shift to online learning. Many learning style models have been widely used and evaluated for their performance in supporting adaptive learning. However, implementing Multiple Intelligence Learning Styles (MILS) remains limited in online learning due to low detection performance. This study employs machine learning approaches to enhance the detection performance of Multiple Intelligence Learning Styles. This study proposes an integrated machine learning framework to enhance MILS classification by combining data preprocessing, log-modulus transformation, and class imbalance handling via Synthetic Minority Over-Sampling Technique (SMOTE), Adaptive Synthetic Sampling Approach (ADASYN), and SMOTE-Tomek. Recursive Feature Elimination (RFE) with Support Vector Machine (SVM) is used for feature selection while eight machine learning models are used for classification. Interactions between learners and the Learning Management System (LMS) comprise the dataset, which are labeled using the Multiple Intelligence Inventory. The SVM model using ADASYN outperforms previous studies and other models, achieving the highest F1-Score of 89%, according to experimental data using 5-fold cross-validation. Statistical tests (Shapiro-Wilk, Analysis of variance (ANOVA), and paired t-tests) confirm significant differences in performance between models. The proposed approach demonstrates enhanced detection performance and can be adapted to broader e-learning applications, supporting adaptive and personalized learning systems.

The objectives of the research were to find out whether a) students’ achievement in reading comprehension taught by using Jigsaw model was higher than taught by using Task-Based Learning (TBL) b) students’ achievement in reading comprehension with visual style was higher than that students with auditory style. The population was the students of SMA Budi Murni 2 Medan with 104 students. The samples were 3 parallel classes and two classes by applying cluster random sampling. The questionnaire was administered for classifying the students upon the visual and auditory learning style. The data were analyzed by applying two-way analysis of variance (ANOVA) at the level of significance α= 0.05. The result proved that students’ achievement in reading comprehension taught by using Jigsaw was higher than that taught by using TBL, students’ achievement in reading comprehension with visual learning style was higher than those with auditory learning style and there was interaction between models of learning and learning styles on students’ achievement in reading comprehension. Moreover, Tuckey-test result also showed that visual style students got higher achievement if they were taught by using Jigsaw model while auditory style students got higher achievement if they were taught by using TBL model. Keywords: Effect; Models of Learning; Reading Comprehension; Students’ Learning Style; Students’ Achievement

This review paper analyzes significant studies in learning style and e-Learning fields in order to synthesize an answer to the question “Does considering learning styles improve e-Learning performance especially for K-12 mathematics education?”. Included studies can be categorized into the following topics: learning style models, learning style detection methods, considering learning styles in traditional education and e-Learning, considering learning styles in K-12 mathematics education. The review shows that applying different teaching methods for different learning styles could actually help a K-12 student understand a mathematics subject

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.

Matching learning style to instructional format penalizes learning

In a student-centered teaching and learning environment, students' needs, potentials, and learning styles are considered crucial. Therefore, teachers need to understand what learning styles students prefer to teach effectively. In the current study, a quantitative research approach has been adopted in this study within it descriptive research designed was used. To determine the preferred learning styles of B.Ed. students, VARK (Visual, Aural, Read/Write, and Kinesthetic) learning style model has been used. Since the data was collected using the VARK questionnaire, simple random sampling techniques were used. The reliability of the instrument was calculated through Cronbach α= 0.75. The sample of the study consists of 140 Bachelor of Education (B.Ed.) students of a Public Sector University located in Northern Sindh, Pakistan. The data were analyzed through descriptive statistics (percentages mean and standard deviation) to determine the most preferred style of learning of students. The results of the study revealed that 27.93% of the B.Ed. students have preferred aural learning style, 25.13% kinaesthetic learning style, 22.65% visual style of learning and 21.09% preferred read/write learning style respectively. To conclude that the majority of the B.Ed. students preferred aural learning style and the least preferred style of learning was read/write. Hence, B.Ed. students were driven towards an aural learning style. This study suggests that students learning styles are influenced by the teacher’s teaching style. Therefore, the teacher can determine his/her teaching style by using the score of the VARK questionnaire. The study recommends that another study can be conducted by the teachers to learn about the larger number of students’ preferred learning styles. The teacher can also address a mixture of learning styles. In the classroom, there are always diverse learners. In that case, the teacher can use integrated teaching style which can address all learners preferred teaching style.

Adaptation to learners’ learning styles can help education systems improve learning efficiency and effectiveness. This research orientation has been studied by many researchers lately, but most of the existing education systems lack adaptation in which every learner is delivered the same learning content. Moreover, many researchers concluded that it is worth applying automatic identification of learning style because of its advantages in precision and time savings. In our study, we concentrate on two main technologies to implement adaptation in education systems: semantic web and intelligent agents. Using ontology with the Semantic Web services makes it faster and more convenient to query and retrieve educational materials. Intelligent agents can provide the learners with personal assistants to carry out learning activities according to their learning styles and knowledge level. In this paper, we present a domain ontology that is suitable for adaptive e-learning environments. The ontology describes the learning objects that compose a course as well as the learners and their learning styles. We also present a multi-agent e-learning system that supports pre-defining and re-examining students’ learning styles during the course for better personalization. In the system, the learning style of each learner can be identified automatically and dynamically. We used a new literature-based method that uses learners’ behaviors on learning objects as indicators for this task. The evaluation showed a high precision in detecting learning styles and in delivering learning materials. Together with the mentioned benefits, this result indicates that our e-learning system is capable of wide use. !

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.

A growing body of research suggests that increased learning gains can be achieved with college students when instruction is designed with learning styles in mind. In addition, several practitioners within the domains of science and engineering education have noted the importance of embedding a learning style approach within a variety of teaching strategies. Furthermore, attention to learning styles and learner diversity has been shown to increase student motivation to learn. In this interactive workshop, the research base on teaching and learning styles was outlined. Emphasis was placed on specific applications of teaching and learning styles in science, mathematics, engineering, and technology (SMET) education. Additional emphasis was placed on the critical role that a learning style approach can play in terms of SMET education. This workshop begins with an overview of several available learning style models and instruments. Information regarding how to choose the right assessment tool(s) for use with science, mathematics, engineering and technology students was shared. In addition, a description of some of the highlights of reported studies and programs involving learning styles in SMET education were given.

Background: Critical thinking is an important thing possessed by the students as an order thinking skills which support independent and research-based learning for students. One attempt to fulfill the scientific learning process is conduct a project-based learning by taking into account the motivation and learning styles of students. This study aimed to identify the effect of project based learning, motivation, and visual, auditory and kinesthetic (VAK) learning styles on high school students’ critical thinking skills of the ecosystem topic. This research used quasi-experiment with 2x2x3 factorial design. Research was conducted on high school students in grade 10th in Jakarta as many as 348 students were taken by simple random sampling technique. Data was collected by a motivation and VAK learning style questionnaire and critical thinking skills test. Data was analyzed by General Linear Model Uni-variate ANOVA at α = 0.05. The whole group had a normal distributed and homogeneous data. The results showed that (1) there is the significant effect of the Project-based learning on students' critical thinking skills, (2) motivation affects students' critical thinking skills, (3) VAK learning style does not affect students' critical thinking skills, (4) the interaction between the two independent variables was fitted (learning models*motivation , learning models*VAK learning styles , and motivation * VAK learning style )and does not affect student’s critical thingking skills, and (5) interaction model of learning , motivation , and learning styles affect the students' critical thinking skills. Based on the results above, students’ critical thinking ability can be improved through the project-based learning by taking into several factors such as students’ motivation and 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%.

An evolving learning style detection approach for online education using bipartite graph embedding

A juggling act in the classroom: Managing different learning styles

Mathematical representation ability is one of the essential and fundamental components that students need to express their mathematical ideas during the learning process. However, field observations show that students' ability to represent mathematical ideas is still relatively low, including those related to the topic of quadrilaterals. This condition is influenced by the diversity in students’ learning processes, one of which is caused by differences in learning styles. To investigate this issue, a study is needed to obtain a comprehensive description of students' forms of mathematical representation in solving quadrilateral problems, viewed from the perspective of their learning styles. The learning style used in this study is Honey and Mumford's learning style model. This study employed a qualitative approach with a phenomenological design. The subjects of the study were three eighth-grade students from MTsN in Mataram City. The data collection techniques used in this study were questionnaires, tests, and interviews. The results showed that students with an activist learning style tend to experience difficulties in modeling their ideas geometrically when solving problems related to quadrilaterals. They were less able to model and interpret problems in detail. However, when faced with problems that involved representing their ideas to find solutions to real-life situations, in general, students with an activist learning style were able to find appropriate solutions.