E-learning Recommender Research Articles

A hybrid E-learning recommendation integrating adaptive profiling and sentiment analysis

This research proposes a novel framework named Enhanced e-Learning Hybrid Recommender System (ELHRS) that provides an appropriate e-content with the highest predicted ratings corresponding to the learner’s particular needs. To accomplish this, a new model is developed to deduce the Semantic Learner Profile automatically. It adaptively associates the learning patterns and rules depending on the learner’s behavior and the semantic relations computed in the semantic matrix that mutually links e-learning materials and terms. Here, a semantic-based approach for term expansion is introduced using DBpedia and WordNet ontologies. Further, various sentiment analysis models are proposed and incorporated as a part of the recommender system to predict ratings of e-learning resources from posted text reviews utilizing fine-grained sentiment classification on five discrete classes. Qualitative Natural Language Processing (NLP) methods with tailored-made Convolutional Neural Network (CNN) are developed and evaluated on our customized dataset collected for a specific domain and a public dataset. Two improved language models are introduced depending on Skip-Gram (S-G) and Continuous Bag of Words (CBOW) techniques. In addition, a robust language model based on hybridization of these couple of methods is developed to derive better vocabulary representation, yielding better accuracy 89.1% for the CNN-Three-Channel-Concatenation model. The suggested recommendation methodology depends on the learner’s preferences, other similar learners’ experience and background, deriving their opinions from the reviews towards the best learning resources. This assists the learners in finding the desired e-content at the proper time.

E-Learning Recommendation System for Big Data Based on Cloud Computing

In educational institutions, E-learning has been known as a successful technology for enhancing performance, concentration, and thus providing higher academic success. Nevertheless, the conventional system for executing research work and selecting courses is a time-consuming and unexciting practice, that not only directly impacts the students ’ academic achievement but also impacts the learning experience of students. In addition to that, there is an enormous number of various kinds of data in the E-Learning domain both structured and unstructured, and the academic establishments attempt to manage and understand big complicated data sets. To fix this problem, this paper proposes a model of an E-learning recommendation system that will suggest and encourage the learner in choosing the courses according to their needs. This system used big data tools such as Hadoop and Spark to enhance data collection, storage, analysis, processing, optimization, and visualization, furthermore based on cloud computing infrastructure and especially Google cloud services.

An Analysis of learners’ affective and cognitive traits in Context-Aware Recommender Systems (CARS) using feature interactions and Factorization Machines (FMs)

Massive Open Online Courses (MOOCs) have witnessed a fast emergence in recent years thanks to their open and massive nature. A huge number of learners with different profiles, knowledge and learning objectives follow the same online courses with different personalized experiences. With this rapid development, course recommendation based on traits and characteristics becomes a necessity during the learning process to determine potentially suitable learning objects while analyzing user’s behaviours. Context-Aware Recommender Systems (CARS) have been shown to be effective in recommending items according to user’s interests and affect. In this paper, we propose a novel approach for Context-Aware Recommender Systems based on Factorization Machines (FMs). We propose a new algorithm called Unsupervised Graph Predictor Factorization Machines (UGPFMs) that models feature interactions during the recommendation process. UGPFMs apply Convolutional Neural Networks (CNNs) in the graph predictor to model interactions between context features in the rating matrice, then it employs the Factorization Machine (FM) to select the suitable items for the recommendation. UGPFM is a generic model that extends FM to improve the accuracy of recommendation, it outperforms state-of-the-art feature interactions-based FM techniques using MSE, RMSE, MAE and R-Squared metrics. We applied UGPFMs on MOOC while considering the sentiment, the cognition and the confusion as contexts for the recommendation. We compared different context combinations’ impact on the recommendation accuracy, then we computed each context-to-context feature interactions to better understand each context efficiency on e-learning recommendation.

An efficient e-learning recommendation system for user preferences using hybrid optimization algorithm

An efficient e-learning recommendation system for user preferences using hybrid optimization algorithm

Ontology-based E-learning Content Recommender System for Addressing the Pure Cold-start Problem

E-learning recommender systems are gaining significance nowadays due to its ability to enhance the learning experience by providing tailor-made services based on learner preferences. A Personalized Learning Environment (PLE) that automatically adapts to learner characteristics such as learning styles and knowledge level can recommend appropriate learning resources that would favor the learning process and improve learning outcomes. The pure cold-start problem is a relevant issue in PLEs, which arises due to the lack of prior information about the new learner in the PLE to create appropriate recommendations. This article introduces a semantic framework based on ontology to address the pure cold-start problem in content recommenders. The ontology encapsulates the domain knowledge about the learners as well as Learning Objects (LOs). The semantic model that we built has been experimented with different combinations of the key learner parameters such as learning style, knowledge level, and background knowledge. The proposed framework utilizes these parameters to build natural learner groups from the learner ontology using SPARQL queries. The ontology holds 480 learners’ data, 468 annotated learning objects with 5,600 learner ratings. A multivariate k-means clustering algorithm, an unsupervised machine learning technique for grouping similar data, is used to evaluate the learner similarity computation accuracy. The learner satisfaction achieved with the proposed model is measured based on the ratings given by the 40 participants of the experiments. From the evaluation perspective, it is evident that 79% of the learners are satisfied with the recommendations generated by the proposed model in pure cold-start condition.

Towards an Evolution of E-Learning Recommendation Systems: From 2000 to Nowadays

In e-learning, recommendation systems have proven to be highly efficient for improving learners' performance and knowledge. They can manage the different pedagogical resources and simplify the workload for the instructor and learners as well. Throughout the years, recommendation systems in e-learning have wit-nessed a major evolution since the 2000s. Several aspects have been developed, including techniques involved, test data (...). In this respect, this paper analyses the evolution of recommendation systems in e-learning since 2000 with a focus on the evolution sides. It furthermore addresses areas not fully addressed to date. A set of recommendation systems is identified and then analysed in order to define techniques used, as well as algorithms deployed.

An ontology-based hybrid e-learning content recommender system for alleviating the cold-start problem

An e-learning recommender system (RS) aims to generate personalized recommendations based on learner preferences and goals. The existing RSs in the e-learning domain still exhibit drawbacks due to its inability to consider the learner characteristics in the recommendation process. In this paper, we are dealing with the new user cold-start problem, which is a major drawback in e-learning content RSs. This problem can be mitigated by incorporating additional learner data in the recommendation process. This paper proposes an ontology-based (OB) content recommender system for addressing the new user cold-start problem. In the proposed recommendation model, ontology is used to model the learner and learning objects with their characteristics. Collaborative and content-based filtering techniques are used in the recommendation model to generate the top N recommendations based on learner ratings. Experiments were conducted to evaluate the performance and prediction accuracy of the proposed model in cold-start conditions using the evaluation metrics mean absolute error, precision and recall. The proposed model provides more reliable and personalized recommendations by making use of ontological domain knowledge.

Deep auto encoders to adaptive E-learning recommender system

Adaptive learning, supported by Information & Communication Technology (TIC), is an important research area for educational systems which aim to improve the outcomes of students. Thus, the investigation of what should be adapted and how much to adapt constitute a foundation to Adaptive E-learning Systems (AES). In this paper, we compared three classes of Deep Auto Encoders and the popularity model to address the problem of learning and predicting the preferences of student on AES: Collaborative Denoising Auto Encoders (CDAE), Deep Auto Encoders for Collaborative Filtering (DAE-CF), and Deep Auto Encoders for Collaborative Filtering using Content Information (DAE-CI). The results point out that the DAE-CF is more effective providing significant adaptability. Furthermore, we present the concept named as signature of preference to represent a more granular class of adaptability. Therefore, this model may be used in e-learning systems to provide adaptability and help to improve the outcomes of students.

An E-learning recommender system using switch hybridization

A recommender system is developed to improve the efficient performance of new learners using stereotype filtering and collaborative filtering. The paper aimed at adopting a model that follows a classification of recommendation based on information sources that are being used, such as user profile and user-item profile to make accurate recommendation to new learners. The system undertakes stereotype filtering because it is less sensitive to the new learner. In stereotype filtering, recommendations are issued to new user by first identifying the category they belongs to and locating preferences of other users in the same category. The proposed system combines both recommendation techniques in order to gain better performance and address the shortcomings of each. The result showed that the satisfaction level are based on learner academic Information. Privacy issues should be explored in gaining learner’s loyalty as well as frequent feedback. Hence, there is need for developing additional facilities to preserve privacy information and at the same time be able to use them for accurate recommendation.

WITHDRAWN: A comprehensive study on recommendation systems their issues and future research direction in e-learning domain

Abstract With the advent of World Wide Web a significant number of institutions, universities and companies have started doing their business online. However, in this scenario a huge amount of items are presented to the user online which makes it difficult for a user to choose the right item which best matches with their preferences. This motivates researchers to build a recommendation engine which suggests right items to users based on their profile. A recommendation systems help out the end user by presenting a list of items to choose from the vast repository of items. The function of a recommendation system is to predict the ratings of unseen items by a user and recommends the top N items which might be of interest to the end user. Today’s recommendation system based their recommendations solely on users’ profile which disregards other crucial information about users’ preferences which could further improve the quality of recommendations. This users’ profile is not sufficient to make good quality of recommendations and can be further enriched by exploiting additional information about learners such as learners’ contextual data, tagging data of learner in social networking sites and learners’ semantic information underlying a website among others. Keeping this in mind, new recommendation approaches need to be developed which can extract and combine this additional data about learners into the recommendation process. This paper aims to survey existing recommendation techniques, their algorithms, discusses their issues and provides research directions for developing smart E-Learning recommender systems.

E-Learning Recommended System

In Hybrid e-learning recommender frameworks, to share the data between researcher is deficient, which makes it difficult to apply cross breed filtering (HF) proposal framework. We propose a communitarian filtering (CF) methods utilizing memory based separating to beat the issues which we experienced on crossover sifting strategies. Memory-based separating procedures utilize the whole client thing dataset to make various neighborhoods of clients. Neighborhood-based calculation decide the likeness between two clients or things, and produces an expectation for the client by taking the weighted normal of the considerable number of appraisals. Influence engendering implies that a student can advance toward dynamic students, and such practices can invigorate the moving practices of his neighbors. This self-association based suggestion approach accomplishes a steady structure dependent on circulated and base up practices of people. The trial results exhibit that memory based sifting strategies to give customized and diversified suggestions in e-learning situations.

A Personalized Web Based E-Learning Recommendation System to Enhance and User Learning Experience

The key aim of the data mining techniques is to help the user by reducing the effort for exploring the data, recovering the patterns, and implementing applications that help to find the knowledge specific contents, decision making, and predictions. This research work develops a recommendation system by using the merits of data mining algorithms. They are used for designing web-based e-learning recommendation systems. This model aims to understand the user behavior and contents requirements of the learner. This purpose is solved by obtaining the information from the data source and producing the suggestions of suitable content to the learner. The concept of web content mining and web usage mining has been combined together for performing the required work. This technique involves the genetic algorithm and k-means clustering algorithm for designing the presented model. In this work the k-means clustering algorithm has been used to track user behavior and the genetic algorithm has been used as a search algorithm to find the necessary resources in the database. Finally, the presented system is implemented and its performance is measured. The estimated results demonstrate that the presented model enhances the accuracy of recommendations and also speeds up the computations. A related performance calculation has also provided to justify this conclusion. The obtained results demonstrate that this technique is acceptable for new generation application designs.

A Hybrid E-Learning Recommendation Approach Based on Learners’ Influence Propagation

In e-learning recommender systems, interpersonal information between learners is very scarce, which makes it difficult to apply collaborative filtering (CF) techniques to achieve recommendations. In this study, we propose a hybrid filtering recommendation approach (SI - IFL) combining learner influence model (LIM), self-organization based (SOB) recommendation strategy, and sequential pattern mining (SPM) together for recommending learning objects (LOs) to learners. The method works as follows: (i) LIM is applied to acquire the interpersonal information by computing the influence that a learner exerts on others. LIM consists of learner similarity, knowledge credibility, and learner aggregation, meanwhile, LIM is independent of ratings. Furthermore, to address the uncertainty and fuzzy natures of learners, intuitionistic fuzzy logic (IFL) is applied to optimize the LIM. (ii) A SOB recommendation strategy is applied to recommend the optimal learner cliques for active learners by simulating the influence propagation among learners. Influence propagation means that a learner can move towards active learners, and such behaviors can stimulate the moving behaviors of his/her neighbors. This SOB recommendation approach achieves a stable structure based on distributed and bottom-up behaviors of individuals. (iii) SPM is applied to decide the final learning objects (LOs) and navigational paths based on the recommended learner cliques. The experimental results demonstrate that SI - IFL can provide personalized and diversified recommendations, and it shows promising efficiency and adaptability in e-learning scenarios.

Semantically enhanced machine learning approach to recommend e-learning content

E-learning platforms contain a large number of heterogeneous resources of knowledge. In current e-learning systems, learners spend a lot of time and effort trying to find relevant learning resources. It is necessary to consider the learner's true needs according to different factors, such as learning style, experience, and preferences. Learning needs to be relevant to the context of the required concept. This work presents analytical review of the current status of e-learning system design. A new approach based on machine learning (ML) combined with ontology techniques has been suggested to develop an efficient e-learning recommender system. The proposed model uses Bayesian inference algorithm to predict learning materials, which are collected and indexed within the system. Ontology has been used to expand the initial terms extracted. Semantic relation between the learning material and the term was generated and fed to the model. Experimental results using this model show promising performance.

The research trends in recommender systems for e-learning

Purpose A recommendation algorithm is typically applied to speculate on users’ preferences based on their behavioral characteristics. The purpose of this paper is to provide a systematic review of recommendation systems by collecting related journal articles from the last five years (i.e. from 2014 to 2018). This paper aims to study the correlations between recommendation technologies and e-learning systems. Design/methodology/approach The paper reviews the relevant articles using five assessment aspects. A coding scheme was put forward that includes the following: the metrics for the e-learning system, the evaluation metrics for the recommendation algorithms, the recommendation filtering technology, the phases of the recommendation process and the learning outcomes of the system. Findings The research indicates that most e-learning systems will adopt the adaptive mechanism as a primary metric, and accuracy is a vital evaluation indicator for recommendation algorithms. In existing e-learning recommender systems, the most common recommendation filtering technology is hybrid filtering. The information collection phase is an important process recognized by most studies. Finally, the learning outcomes of the recommender system can be achieved through two key indicators: affections and correlations. Originality/value The recommendation technology works effectively in closing the gap between the information producer and the information consumer. This technology could help learners find the information they are interested in as well as send them a valuable message. The opportunities and challenges of the current study are discussed; the results of this study could provide a guideline for future research.

New Empirical Data Findings for Student Experiences of E-Learning analytics Recommender Systems and their Impact on System Adoption

This article examines Saudi Arabian students' experiences of using an e-learning analytics recommender system during their study and the extent to which their experiences were predictors of their adoption and post-adoption of the system. A sample of 353 students from various universities in Saudi Arabia completed a survey questionnaire for data collection. Results showed that user experience is a significant predictors of student adoption and post-adoption of an e-learning recommender system. Based on these findings, this study concluded that universities must support students to develop their awareness of, and skills in using an e-learning recommender system to support students' long-term acceptance and use of the system.

An intelligent fuzzy rule-based e-learning recommendation system for dynamic user interests

A relevant and suitable content recommendation is an important and challenging task in e-learning. Relevant terms are retrieved in a recommender system that should also cope with varying user preferences over time. This paper proposes a novel recommendation system which provides suitable contents by refining the final frequent item patterns evolving from frequent pattern mining technique and then classifying the final contents using fuzzy logic into three levels. This is achieved by generating frequent item patterns after consolidating the user interest changes with an extended error margin quotient. Moreover, fuzzy rules are used in this work to enable the rule mining constraints for accommodating all types of learners while applying rules on the pattern tables. This method aims at mining the data stream preferences into equal-sized windows and caters to the varying user interest ratings over time. Experiments prove its efficiency and accuracy over existing conventional methods.

A Comprehensive Survey of Neighborhood-Based Recommendation Methods used in E-Learning Recommender Systems

A Comprehensive Survey of Neighborhood-Based Recommendation Methods used in E-Learning Recommender Systems

Large-scale e-learning recommender system based on Spark and Hadoop

The present work is a part of the ESTenLigne project which is the result of several years of experience for developing e-learning in Sidi Mohamed Ben Abdellah University through the implementation of open, online and adaptive learning environment. However, this platform faces many challenges, such as the increasing amount of data, the diversity of pedagogical resources and a large number of learners that makes harder to find what the learners are really looking for. Furthermore, most of the students in this platform are new graduates who have just come to integrate higher education and who need a system to help them to take the relevant courses that take into account the requirements and needs of each learner. In this article, we develop a distributed courses recommender system for the e-learning platform. It aims to discover relationships between student’s activities using association rules method in order to help the student to choose the most appropriate learning materials. We also focus on the analysis of past historical data of the courses enrollments or log data. The article discusses particularly the frequent itemsets concept to determine the interesting rules in the transaction database. Then, we use the extracted rules to find the catalog of more suitable courses according to the learner’s behaviors and preferences. Next, we deploy our recommender system using big data technologies and techniques. Especially, we implement parallel FP-growth algorithm provided by Spark Framework and Hadoop ecosystem. The experimental results show the effectiveness and scalability of the proposed system. Finally, we evaluate the performance of Spark MLlib library compared to traditional machine learning tools including Weka and R.

A Framework for Adaptive Personalized E-learning Recommender Systems

With the undergoing technological revolution in education, adapting recommender systems to the personalized e-learning is an emerging topic in the education sector. Detecting the student model offers a potential to recommend a learning material that is adequate to the student progress. Accordingly, the learning objects and hypermedia can be adapted to each individual student to meet the personalized learning needs. This paper proposes a framework for applying recommender systems in personalized e-learning domain. Furthermore, the recommender system previous examples, opportunities, and associated challenges are discussed.