scholarly journals Design and Analysis of a Cluster-Based Intelligent Hybrid Recommendation System for E-Learning Applications

Mathematics ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 197
Author(s):  
Sundaresan Bhaskaran ◽  
Raja Marappan ◽  
Balachandran Santhi
Keyword(s):  
Recommendation System ◽  
Pattern Mining ◽  
Absolute Error ◽  
Learning Systems ◽  
Linear Pattern ◽  
Significant Difference ◽  
Functional Patterns ◽  
E Learning ◽  
Error Metric ◽  
Customized Learning

Recently, different recommendation techniques in e-learning have been designed that are helpful to both the learners and the educators in a wide variety of e-learning systems. Customized learning, which requires e-learning systems designed based on educational experience that suit the interests, goals, abilities, and willingness of both the learners and the educators, is required in some situations. In this research, we develop an intelligent recommender using split and conquer strategy-based clustering that can adapt automatically to the requirements, interests, and levels of knowledge of the learners. The recommender analyzes and learns the styles and characteristics of learners automatically. The different styles of learning are processed through the split and conquer strategy-based clustering. The proposed cluster-based linear pattern mining algorithm is applied to extract the functional patterns of the learners. Then, the system provides intelligent recommendations by evaluating the ratings of frequent sequences. Experiments were conducted on different groups of learners and datasets, and the proposed model suggested essential learning activities to learners based on their style of learning, interest classification, and talent features. It was experimentally found that the proposed cluster-based recommender improves the recommendation performance by resulting in more lessons completed when compared to learners present in the no-recommender cluster category. It was found that more than 65% of the learners considered all criteria to evaluate the proposed recommender. The simulation of the proposed recommender showed that for learner size values of <1000, better metric values were produced. When the learner size exceeded 1000, significant differences were obtained in the evaluated metrics. The significant differences were analyzed in terms of a computational structure depending on L, the recommendation list size, and the attributes of learners. The learners were also satisfied with the accuracy and speed of the recommender. For the sample dataset considered, a significant difference was observed in the standard deviation σ and mean μ of parameters, in terms of the Recall (List, User) and Ranking Score (User) measures, compared to other methods. The devised method performed well concerning all the considered metrics when compared to other methods. The simulation results signify that this recommender minimized the mean absolute error metric for the different clusters in comparison with some well-known methods.

Towards Increasing the Efficiency of E-Learning Systems Using Recommendation System Approach

2020 ◽  
pp. 35-55
Author(s):  
Zameer Gulzar ◽  
L. Arun Raj ◽  
A. Anny Leema
Keyword(s):  
System Approach ◽  
Recommendation System ◽  
Learning Systems ◽  
Learning Objectives ◽  
Learning System ◽  
E Learning ◽  
Flexible Delivery ◽  
Algorithmic Techniques ◽  
Information Optimization ◽  
Almost All

Data mining approaches have been tried in e-learning systems for information optimization and knowledge extraction to make decisions. In recent years, the recommendation system has gained popularity in every field be it e-commerce, entertainment, sports, healthcare, news, etc. However, in e-learning system, the recommender systems were not effectively utilized in comparison to other domains and thus emerged as a bottleneck for almost all e-learning systems for not offering flexible delivery of the learning resources. Current e-learning systems lack personalization features, and the information is presented in a static way despite their varying learning objectives and needs. The aim of recommender system is to personalize the information with respect to learner interest. The objective of this study is to highlight various algorithmic techniques that can be used to improve information retrieval process to provide effective recommendations to learners for improving their performance and satisfaction level.

Discovering Learners' Characteristics Through Cluster Analysis for Recommendation of Courses in E-Learning Environment

2019 ◽  
Vol 15 (1) ◽  
pp. 42-66
Author(s):  
Bhupesh Rawat ◽  
Sanjay K. Dwivedi
Keyword(s):  
Cluster Analysis ◽  
Academic Performance ◽  
Learning Environment ◽  
Learning Process ◽  
Recommendation System ◽  
Learning Systems ◽  
Traditional Learning ◽  
Huge Number ◽  
E Learning ◽  
The Web

With the emergence of the web, traditional learning has changed significantly. Hence, a huge number of ‘e-learning systems' with the advantages of time and space have been created. Currently, many e-learning systems are being used by a large number of academic institutions worldwide which allow different users of the system to perform various tasks based on their goals. However, most of these systems follow a ‘one size fits all' approach where same resources are offered to learners irrespective of their unique learning requirements. Therefore, personalization is required as a part of e-learning systems which offers resources to learners based on their profile. This research aims to perform cluster analyses in order to validate clusters created through a k-means algorithm. The clusters will be used to classify a new learner into its appropriate class and recommend relevant courses. Finally, the accuracy of the recommendation is evaluated using various evaluation metrics. The proposed recommendation system helps learners to improve their academic performance and hence overall learning process as well.

scholarly journals Adaptive E-Learning System Using Justification Based Truth Maintenance System

2021 ◽  
Vol 4 (2) ◽  
pp. 44-48
Author(s):  
Tahir Mohammad Ali ◽  
Attique Ur Rehman ◽  
Ali Nawaz ◽  
Wasi Haider Butt
Keyword(s):  
Management System ◽  
Learning Management System ◽  
Learning Systems ◽  
Learning System ◽  
Educational Activities ◽  
Maintenance System ◽  
E Learning ◽  
Truth Maintenance ◽  
Learning Management ◽  
Customized Learning

In most E-learning systems, educational activities are presented in a static way without bearing in mind the particulars or student levels and skills. Personalization and adaptation of an E-learning management system are dependent on the flexibility of the system in providing different learning and content models to individual students based on their characteristics. In this paper, we suggest an Adaptive E-learning system which is providing adaptability with support of justification-based truth maintenance system. The system is accomplished of signifying students with suitable knowledge fillings and customized learning paths based on the student’s profile, interests, and previous results.

scholarly journals An Evaluative Study for the Use Reality of E-Learning Systems and Tools in Teaching and Learning by Faculty Members and Students

2018 ◽  
Vol 8 (1) ◽  
pp. 37 ◽  
Author(s):  
Abdulaziz Aboud Mohammed Asiri ◽  
Hassan Shawky Aly
Keyword(s):  
Teaching And Learning ◽  
Faculty Members ◽  
Learning Systems ◽  
Pedagogical Practices ◽  
Learning Tools ◽  
College Courses ◽  
Teaching College ◽  
Significant Difference ◽  
E Learning ◽  
Very High

The present study aimed to identify the reality of E-Learning systems and tools use (Blackboard) by faculty membersand students in teaching and learning courses at the college of education at Najran University. To achieve this aim,two questionnaires for both faculty members and students were developed. A sample of (60) faculty members and(120) students were selected to take part in the present study. Findings showed that the level of Blackboard use bymale and female faculty members was either high or very high in teaching college courses to students. There was nostatistically significant difference (α=0.05) between faculty members regarding the level of E-Learning tools use andits pedagogical practices due to gender and experience. Findings also revealed that male and female students' level ofBlackboard use was very high in studying the college courses. Furthermore, there was no statistically significantdifference (α=0.05) between students regarding the use of E-Learning tools and its pedagogical practices due togender and cumulative average.

scholarly journals Penggalian Perilaku Pemain dalam Penentuan Tipe Permainan pada E-Learning Pemrograman Berbasis Gamification

2020 ◽  
Vol 7 (4) ◽  
pp. 765
Author(s):  
Bayu Priyambadha ◽  
Fajar Pradana ◽  
Fitra Abdurrachman Bachtiar
Keyword(s):  
Online Learning ◽  
Pattern Mining ◽  
Behavior Pattern ◽  
Optimal Number ◽  
Learning Systems ◽  
Learning Goals ◽  
Study Programs ◽  
E Learning ◽  
Common Learning ◽  
Data Log

<p class="Abstrak">Salah satu kompetensi utama yang harus dimiliki oleh lulusan dari jurusan atau program studi bidang keilmuan komputer adalah kemampuan programming (membuat program). Berbagi informasi untuk meningkatkan kualitas pembelajaran pemrograman telah dilakukan di banyak kampus di Indonesia. Salah satunya adalah penerapan media pembelajaran online atau disebut juga sebagai <em>E-Learning</em>. Salah satu sistem pembelajaran yang paling umum, yang didukung oleh teknologi informasi, adalah <em>e-learning</em>. Namun, banyak juga sistem <em>e-learning</em> tidak mencapai tujuan yang diinginkan karena ketidakpatuhan dan kurangnya pengetahuan tentang teknik dan metode untuk pengembangan sistem informasi online. Tujuan yang dicapai antara lain efisiensi, efektifitas, motivasi dan keterlibatan siswa. Pendekatan <em>gamification</em> dapat digunakan untuk meningkatkan beberapa hal tersebut demi tercapainya tujuan pembelajaran <em>online</em>. Dalam sistem Code Maniac, terdapat beberapa elemen <em>gamification</em> yang digunakan, yaitu poin pengalaman, poin aktivitas dan <em>badge</em>. Namun, hal tersebut terbukti masih kurang meningkatkan motivasi mahasiswa dalam menggunakan Code Maniac. Pendekatan <em>player-centric</em> memungkinkan sistem menyesuaikan <em>gameplay</em> yang sesuai dengan gaya bermain seorang pemain. Untuk dapat mewujudkan sebuah media pembelajaran yang berorientasi pada pemain, maka dibutuhkan sebuah mekanisme untuk mengenali karakteristik pemainnya. Pada penelitian ini menekanan metode yang digunakan untuk menggali  perilaku permainan. Penggalian pola dilakukan pada data log proses per pemain dan per sesi yang berjumlah 136 proses. Kemudian proses tersebut dikelompokan sesuai dengan kedekatan atau kesamaan karakteristik bermain. Hasil penentuan jumlah kelompok yang paling optimal adalah k=2 dan k=3. Untuk itu pengelompokan dilakukan dan menghasilkan 2 kelompok dan 3 kelompok data. Kelompok tersebut dapat menjadi dasar untuk untuk penentuan <em>gameplay</em> pada Code Maniac.</p><p class="Abstrak"> </p><p class="Abstrak"><em><strong>Abstract</strong></em></p><p class="Abstract"><em>One of the main competencies that must be possessed by graduates of departments or study programs in computer science is programming skills (making programs). Sharing information to improve the quality of programming learning has been done on many campuses in Indonesia. One of them is the application of online learning media or also called the E-Learning.. One of the most common learning systems, supported by information technology, is e-learning. However, many e-learning systems do not achieve the desired goals because of non-compliance and lack of knowledge about techniques and methods for developing information systems online. The objectives achieved include efficiency, effectiveness, motivation and student involvement. The gamification approach can be used to improve some of these things in order to achieve online learning goals. In the Code Maniac system, there are several gamification elements used, namely experience points, activity points and badges. However, this proved to be still lacking in increasing student motivation in using Code Maniac. The player-centric approach allows the system to adjust the gameplay to suit a player's playing style. To be able to realize a player-oriented learning media, a mechanism is needed to recognize the characteristics of the players. In this study emphasizes the methods used to explore game behavior. Pattern mining is performed on process log data per player and per session which amounts to 136 processes. Then the process is grouped according to the closeness or similarity of playing characteristics. The results of determining the most optimal number of groups are k = 2 and k = 3. For this reason, grouping is done and produces 2 groups and 3 groups of data. The group can be the basis for determining the gameplay in Code Maniac.</em></p><p class="Abstrak"><em><strong><br /></strong></em></p>

A Web-Based Recommendation System for Engineering Education E-Learning Systems

2016 ◽  
pp. 279-291
Author(s):  
Thorsten Sommer ◽  
Ursula Bach ◽  
Anja Richert ◽  
Sabina Jeschke
Keyword(s):  
Engineering Education ◽  
Recommendation System ◽  
Learning Systems ◽  
Web Based ◽  
E Learning

scholarly journals Adjusting Felder-Silverman learning styles model for application in adaptive e-learning

Psihologija ◽  
2012 ◽  
Vol 45 (1) ◽  
pp. 43-58 ◽  
Author(s):  
Djordje Mihailovic ◽  
Marijana Despotovic-Zrakic ◽  
Zorica Bogdanovic ◽  
Dusan Barac ◽  
Vladimir Vujin
Keyword(s):  
Data Mining ◽  
Data Analysis ◽  
Learning Styles ◽  
Learning Systems ◽  
Questionnaire Data ◽  
Data Mining Techniques ◽  
Significant Difference ◽  
E Learning ◽  
Using Data ◽  
Experimental Group

This paper presents an approach for adjusting Felder-Silverman learning styles model for application in development of adaptive e-learning systems. Main goal of the paper is to improve the existing e-learning courses by developing a method for adaptation based on learning styles. The proposed method includes analysis of data related to students characteristics and applying the concept of personalization in creating e-learning courses. The research has been conducted at Faculty of organizational sciences, University of Belgrade, during winter semester of 2009/10, on sample of 318 students. The students from the experimental group were divided in three clusters, based on data about their styles identified using adjusted Felder-Silverman questionnaire. Data about learning styles collected during the research were used to determine typical groups of students and then to classify students into these groups. The classification was performed using data mining techniques. Adaptation of the e-learning courses was implemented according to results of data analysis. Evaluation showed that there was statistically significant difference in the results of students who attended the course adapted by using the described method, in comparison with results of students who attended course that was not adapted.

scholarly journals Development of Electronic Resources on the Formation of Personal Qualities of Schoolchildren

2020 ◽  
Vol 8 (4) ◽  
pp. 777-783
Author(s):  
Orynbayeva Laura Kanybekovna ◽  
◽  
Kosherbaeva Aigerim Nuralievna ◽  
Grinshkun Vadim Valerevich ◽  
Bidaibekov Yesen Yklasovich ◽  
...  
Keyword(s):  
Secondary School ◽  
Learning Environment ◽  
Educational Process ◽  
Learning Systems ◽  
Practical Training ◽  
Web Based ◽  
Qualitative Approaches ◽  
Significant Difference ◽  
E Learning ◽  
Web Based System

The new technology era is shifting the traditional ways of seeking knowledge and plays a new role in disseminating and sharing knowledge. E-learning systems have been introduced with the emergence of and developments in information technology (IT). However, most e-learning systems focus on allowing students to access and use official educational content, with less attention being paid to involve e-resources linked to curricula to support the educational process and the learners. The main objective of this research is to empower users in an e-learning environment with an Information Communication Technology (ICT) web-based system in order to play a bigger role in seeking and sharing e-resources for a better understanding of the curricula. The article focuses on the problem of teaching students in e-learning. The results of a survey helped us identify the main difficulties facing students when they begin their studies. We also describe a methodology of teaching using e-learning as web-based instruction. The use of e-learning in the educational process improves the quality of practical training and provides a better understanding of the course. This study proposes a web-based system that integrates elements of e-resources within an e-learning environment by using e-classes of 7th, 8th, and 9th grades enrolled at Secondary School as a testbed. The system deals with a set of learning cycles that support the aims of e-learning. The first cycle is the student; the second cycle is the teacher. In this study, quantitative and qualitative approaches have been used to evaluate, investigate, and compare the system's impact. The results of this study revealed that there is a significant difference between the students according to grade. Therefore, students at Secondary School would benefit from a system that exposes them to e-resources linked directly to the curriculum to achieve and navigate knowledge understanding.

Sign in / Sign up

Export Citation Format

Share Document