Search

Abstract.Cloud computing is quickly expanding, with applications in practically every industry, including education. E-learning systems often necessitate a large number of hardware and software resources. Many educational institutions cannot afford such investments, thus cloud computing is the best solution. Here, the Matrix Factorisation-based maximum rate recommendation system (MatFac-Maxirate RS) is utilised to recommend the courses for students to choose their career. According to user access, the e-learning application server is acquired from the E-Khool dataset which is subjected to learner or course agglomerative matrix calculation. The E-learning application server is executed based on Minkowski and Kumar Hasebrook's distance to retrieve learner preference items. The recommended course having the maximum rating is considered which is forecasted with matrix factorisation considering the course ID and learner ID. The MatFac-Maxirate RS generated the finest efficacy with the best precision of 88.9%, recall of 88.2% and F-measure of 87.5%. [ABSTRACT FROM AUTHOR]

In recent years, massive online open courses (MOOCs) platforms provide users with a wealth of learning resources. Nevertheless, information overload remains a pressing concern, necessitating the development of effective personalized course recommendation methods. The existing course recommendation methods disregard the temporal relationship among courses and are unable to capture long-distance dependencies between them. Simultaneously, personalized course recommendation models designed for interactive sequence modeling are confronted with two key issues: how to extract users’ learning interest representation effectively and how to solve cold-start. Based on this, a graph neural network course recommendation model (GHLS4CR) is proposed, which integrates hot spots and long and short-term interests. This model designs two session graph conversion methods, acyclic timing graph and acyclic shortcut graph, to alleviate the problems of temporal information loss and inability to capture long-distance dependencies in existing methods. This model represents users’ long-term and short-term interests at the graph level, and integrates them with popular course information to achieve personalized recommendations while alleviating cold-start issue. A large number of experiments conducted on the XuetangX public dataset MOOCCourse show that GHLS4CR outperforms mainstream recommendation models such as FISSA and LESSR in the field of personalized course recommendation. Compared with the second best LESSR model, Recall@5 is improved by 13.28%, and MRR@5 is improved by 15.50%.

This paper delves into leveraging deep learning techniques, such as graph neural networks (GNNs), Transformer, and techniques in Large Language Models (LLMs), to enhance course recommendation systems in e-learning platforms. Recommendation methods have some short-comes in the case of online course with less information and choic less logic. Our research proposes novel algorithms that use graph collaborative filtering and sequential recommendation to improve recommendation accuracy and personalization. By analyzing user behavior patterns and course attributes, our approach aims to provide smarter and more efficient course recommendation services, ultimately enhancing learning outcomes and experiences in e-learning environments. This research not only contributes to the advancement of e-learning technology but also provides valuable insights for the broader application of deep learning in smart education. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The rapid development of Massive Open Online Courses (MOOCs) platforms has created an urgent need for an efficient personalized course recommender system that can assist learners of all backgrounds and levels of knowledge in selecting appropriate courses. Currently, most existing methods utilize a sequential recommendation paradigm that captures the user's learning interests from their learning history, typically through recurrent or graph neural networks. However, fewer studies have explored how to incorporate principles of human learning at both the course and category levels to enhance course recommendations. In this article, we aim at addressing this gap by introducing a novel model, named Prerequisite-Enhanced Catory-Aware Graph Neural Network (PCGNN), for course recommendation. Specifically, we first construct a course prerequisite graph that reflects the human learning principles and further pre-train the course prerequisite relationships as the base embeddings for courses and categories. Then, to capture the user's complex learning patterns, we build an item graph and a category graph from the user's historical learning records, respectively: (1) the item graph reflects the course-level local learning transition patterns and (2) the category graph provides insight into the user's long-term learning interest. Correspondingly, we propose a user interest encoder that employs a gated graph neural network to learn the course-level user interest embedding and design a category transition pattern encoder that utilizes GRU to yield the category-level user interest embedding. Finally, the two fine-grained user interest embeddings are fused to achieve precise course prediction. Extensive experiments on two real-world datasets demonstrate the effectiveness of PCGNN compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The open online course (MOOC) platform has seen an increase in usage, and there are a growing number of courses accessible for people to select. An effective method is urgently needed to recommend personalized courses for users. Although the existing course recommendation models consider that users' interests change over time, they often model users' learning records as a single time-granularity sequence and ignore the collaboration between different time-granularity sessions when recommending courses. In addition, most course recommendation models tend to use the deep network, which weakens the memory ability of the model. Few methods simultaneously consider long and short-term interests and individual course interests in the latest session, which results in a decline in model performance. To resolve these problems, we design an innovative personalized course recommendation model that Integrating Multi-granularity Sessions and Multi-type Interests (IMSMI), which converts user-course interaction sequences as multi-granularity sessions and uses different types of attention mechanisms to capture multi-type interests. Meanwhile, we introduce the residual connections to further strengthen the memory capability of IMSMI. Experimental results using the XuetangX dataset available to the public demonstrate that IMSMI significantly surpasses other competing models on evaluation metrics. Compared to the next best model, Recall@3 is increased by 20.50%, and MRR@3 is increased by 18.07%. [ABSTRACT FROM AUTHOR]

Explainable recommendation is important but not yet explored in Massive Open Online Courses (MOOCs). Recently, knowledge graph (KG) has achieved great success in explainable recommendations. However, the e-learning scenario has some unique constraints, such as learners' knowledge structure and course prerequisite requirements, leading the existing KG-based recommendation methods to work poorly in MOOCs. To address these issues, we propose a novel explainable recommendation model, namely Knowledge-aware Reasoning with self-supervised Reinforcement Learning (KRRL). Specifically, to enhance the semantic representation and relation in the KG, a multi-level representation learning method enriches the perceptual information of semantic interactions. Afterward, a self-supervised reinforcement learning method effectively guides the path reasoning over the KG, to match the unique constraints in the e-learning scenario. We evaluate the KRRL model on two real-world MOOCs datasets. The experimental results show that KRRL evidently outperforms state-of-the-art baselines in terms of the recommendation accuracy and explainability. [ABSTRACT FROM AUTHOR]

The article proposes CKGE, a contextualized knowledge graph (KG) embedding approach for explainable talent training course recommendation. It addresses the challenge of providing explainable recommendations by considering different learning motivations. It is reported that CKGE integrates contextualized neighbor semantics and high-order connections as motivation-aware information for effective representation learning of talents and courses.

At present, the course recommendation model of graph collaborative filtering mainly uses bipartite graph modeling to obtain user-course cooperative relationship. However, the bipartite graph lacks the acquisition of user-user and course-course relationship information. In addition, due to the inherent defects of graph convolution, multi-layer graph convolution will cause overfitting problems. Moreover, the existing graph contrastive learning methods to solve the sparsity of recommendation data simply divide nodes into positive and negative pairs, without taking into account that users who have chosen the same course in the recommendation are similar. In contrastive learning, the feature similarity distance of these users should be different.To solve these problems, a course recommendation model based on layer dropout graph differential contrastive learning(DGDCL) is proposed. Specifically, a hybrid graph convolution network of fusion graph and hypergraph is used to obtain both low-order and high-order information. Then, using the layer dropout method to alleviate overfitting in neural network, the multi-layer feature embeddings of graph nodes are randomly dropout. Finally, two different layer drops are used to generate the contrastive views to reduce the additional noise and computational overhead of generating the contrastive views. The prior similarity of users and courses is used to adjust the calculation of the contrastive loss function, and differentiated contrastive learning of graph nodes is realized to make the contrastive learning more suitable for the recommendation model. The experimental results of XuetangX and MOOCCube datasets show that the proposed model is better than the existing model.

Course recommendation is vital for improving students’ learning efficiency. In the learning process, students’ interests evolve, learning cycles and course scheduling are closely related to temporal information. However, previous course recommendation methods discard it as irrelevant, leading to poor recommendation performance. In addition, the lack of explainability of the course recommendations reduces students’ engagement and trust in online learning. To solve two problems, this paper proposes a Learning-motivation-boosted Explainable Temporal point process model for Course Recommendation (LETCR). Firstly, LETCR considers the timestamps in interaction records as absolute time and the sequence of records as relative time, and it calculates the different contributions of historical interaction records to the recommendation results. Secondly, LETCR proposes four factors that affect students’ course selection from the perspective of learning motivation: interest preference, follow relationship, conformity and popular course. Finally, LETCR models these with a temporal point process, so as to improve model’s explainability. Extensive experiments on the MOOCCourse dataset show that LETCR outperforms other advanced recommendation models by 7.09% and 9.28% on R@10 and NDCG@5, respectively, and has high explainability.

In higher education, academic advising is crucial to students' decision-making. Data-driven models can benefit students in making informed decisions by providing insightful recommendations for completing their degrees. To suggest courses for the upcoming semester, various course recommendation models have been proposed in the literature using different data mining techniques and machine learning algorithms utilizing different data types. One important aspect of the data is that usually, courses taken together in a semester fit well with each other. If there is no correlation between the co-taken courses, students may find it more difficult to handle the workload. Based on this insight, we propose using session-based approaches to recommend a set of well-suited courses for the upcoming semester. We test three session-based course recommendation models, two based on neural networks (CourseBEACON and CourseDREAM) and one on tensor factorization (TF-CoC). Additionally, we propose a postprocessing approach to adjust the recommendation scores of any base course recommender to promote related courses. Using metrics capturing different aspects of the recommendation quality, our experimental evaluation shows that session-based methods outperform existing popularity-based, association-based, similarity-based, factorization-based, neural networks-based, and Markov chain-based recommendation approaches. Effective course recommendations can result in improved student advising, which, in turn, can improve student performance, decrease dropout rates, and a more positive overall student experience and satisfaction. [ABSTRACT FROM AUTHOR]

Online learning platforms provide diverse course resources, but this often results in the issue of information overload. Learners always want to learn courses that are appropriate for their knowledge level and preferences quickly and accurately. Effective course recommendation plays a key role in helping learners select appropriate courses and improving the efficiency of online learning. However, when a user is enrolled in multiple courses, existing course recommendation methods face the challenge of accurately recommending the target course that is most relevant to the user because of the noise courses. In this paper, we propose a novel reinforcement learning model named Actor-Critic Hierarchical Reinforcement Learning (ACHRL). The model incorporates the actor-critic method to construct the profile reviser. This can remove noise courses and make personalized course recommendations effectively. Furthermore, we propose a policy gradient based on the temporal difference error to reduce the variance in the training process, to speed up the convergence of the model, and to improve the accuracy of the recommendation. We evaluate the proposed model using two real datasets, and the experimental results show that the proposed model significantly outperforms the existing recommendation models (improving 3.77% to 13.66% in terms of HR@5). [ABSTRACT FROM AUTHOR]

Profiling users' temporal learning interests is key to online course recommendation. Previous studies mainly profile users' learning interests by aggregating their historical behaviors with simple fusing strategies, which fails to capture their temporal interest patterns underlying the sequential user behaviors. To fill the gap, we devise a recommender that incorporates time-aware Transformers and a knowledge graph to better capture users' temporal learning interests. First, we introduce stacked Transformers to extract users' temporal learning interests underlying users' course enrollment sequences. In addition, we design a time-aware positional encoding module to consider the enrollment time intervals between courses. Third, we incorporate a knowledge graph to utilize the latent knowledge connections between courses. The proposed method outperforms state-of-the-art baselines for course recommendation. Furthermore, findings in the ablation study offers several insights for future research. The proposed model can be implemented in online learning platforms to increase user engagement and reduce dropout rate. [ABSTRACT FROM AUTHOR]

This paper applies a nonlinear differential equation to the information management system of college course selection. A teaching information management system based on an approximate learning strategy is presented by using statistical linearization technology. An imprecise controller is obtained by numerical simulation of Riccati differential equations with statistical linearization. This kind of Riccati differential equation differs significantly from the ordinary one. Then the system proposes a collaborative filtering method based on nonlinear differentiation based on student feature classification. At last, this paper systematically analyzes the differences between course selection systems, business recommendations, and student attributes—the system experiments on college students' choice of a learning platform. The study found that the method was correct 34.6% of the time. This system can provide practical guidance for students to choose courses.

With the advent of rapid advancements in information technology, online learning has increasingly gained traction, prompting a multitude of colleges and universities to adopt innovative reforms in their educational delivery methods. This research undertakes the development of a college English online interactive learning system empowered by artificial intelligence. It primarily investigates the interactive behaviors of college students in online English learning environments. Initially, the study employs the K-means algorithm to categorize students based on their distinct learning behaviors. Subsequently, it leverages a recommendation algorithm to fine-tune the provision of English teaching resources online. Furthermore, the study integrates an enhanced Apriori algorithm to extract associations between student behaviors and learning outcomes. This analytical framework underpins the empirical evaluation of the system’s efficacy in actual educational settings, aiming to deepen the understanding of students’ online interactive behaviors. The findings reveal that over 95% of students consistently log into the learning platform on scheduled class days. The metrics for course recommendation success, such as the hit rate, the average inverse rank, and the range of normalized discounted cumulative gain, are reported between 18.37-21.94, 1.87-2.08, and 4.44-4.87, respectively. Additionally, system memory utilization remains stable at 57%-66%, corroborating the system’s operational effectiveness. This research contributes valuable insights and benchmarks for the development of robust online interactive learning systems.

Based on the feasibility of a personalized teaching platform and user requirements, this paper puts forward the overall architecture design and database design scheme of a personalized teaching platform in ideological and political education, which mainly consists of three functional modules, namely, the knowledge mapping module, ideological and political education course recommendation module, and learning effect evaluation module. After crawling the initial data based on the LTP model, the ideological and political education course resources were extracted and integrated to complete the construction of the knowledge graph module. The ideological and political education course recommendation module is created using the KGCNN algorithm, and then the learning effect evaluation module is constructed by combining the online behavior of students. After testing the system’s performance, the application effect of the teaching platform is assessed. The results show that KGCNN aggregation layer space in the interval of 10~100 can embed data with power law distribution more effectively, and the KGCNN algorithm also has certain advantages in the field of modeling personalized teaching platforms for ideological and political education. The number of experimental classes and ordinary classes with final grades in the L1 band increased by 21.90% and 7.17%, respectively, compared to the midterm, indicating that the personalized teaching platform for ideological and political education courses can effectively promote the improvement of student’s academic performance, and the enhancement effect of students with high levels is more significant.

With the rapid development of Internet technology, the number of groups participating in online learning is increasing. Online learning, interaction and communication are becoming more frequent. Online education has gradually formed as a new type of education model. On the one hand, it brings great convenience to students and provides a new way of learning. On the other hand, it also proposes solutions to the phenomenon of "information overload" brought about by the rapid growth of learning resources. A distinctive feature of online education is interest-driven. The traditional online education course recommendation method has poor topic concentration due to the problem of data sparse. For this reason, an online education course recommendation method based on the LDA (Latent Dirichlet Allocation) user interest model is designed, where LDA is an unsupervised machine learning method. The LDA user interest model is used to judge the user's preference for topics, obtain the user's interest in online education courses, and complete the recommendation of online education courses based on this. Finally, the proposed method is evaluated using online learning website data. The comparison results with three online course recommendation methods show that the recommendation method based on the LDA model has better recommendation effect, and the recommended course topics are more concentrated, which is more suitable for application in online education course recommendation. [ABSTRACT FROM AUTHOR]

Nowadays, with more and more physical education curriculum resources, schools or teachers have more and more choices for physical education curriculum resources. However, because some teachers need a deep understanding of curriculum training programs and standards, the selected curriculum resources cannot promote their curriculum development. This paper puts forward the research on the intelligent recognition and game model of physical education curriculum resources based on neural networks. The specific research conclusions are as follows: The intelligent consciousness and movement model of physical education curriculum resources based entirely on the technical knowledge of the BP neural community and deep neural community are proposed. With the help of MATLAB7.1 neural network toolbox to implement the specific recommendation system, a three-layer BP network is established, and the NEWFF function is used to create the neural network. Useful resources in each direction generate a direction recognition vector according to the route guidance standard, calculate the course recommendation degree according to selection statistics and scoring, and input the course resource recognition vector and recommendation degree into the neural network. When the number of hidden layer nodes is 10, and the learning training algorithm selects the L-M optimization algorithm, the error between the actual output and the expected output of the network meets the requirements. [ABSTRACT FROM AUTHOR]

In the MOOCs context, learners experience information overload. Thus, it is necessary to improve personalized recommendation algorithms for learners. The current recommendation algorithm focuses mainly on the learners' course ratings. However, the choice of courses is not only based on the learners' interests and preferences. It is also affected by learners' knowledge domains and learning capabilities, all of which change dynamically over time. Therefore, this study proposes a personalized hybrid recommendation algorithm combining clustering with collaborative filtering. First, data on learners' course rating preferences, course attribute preferences, and multidimensional capabilities that match course traits are used based on multidimensional item response theory. Second, considering that learners' preferences and multidimensional capabilities change dynamically over time, the Ebbinghaus forgetting curve is introduced by integrating memory weights to improve the accuracy and interpretation of the proposed recommendation algorithm for MOOCs. Finally, the performance of the proposed recommendation algorithm is investigated using data from Coursera, an internationally renowned MOOCs platform. The experimental results show that the proposed recommendation algorithm is superior to the baseline algorithms. Accordingly, relevant suggestions are proposed for the development of MOOCs. [ABSTRACT FROM AUTHOR]

To meet the need for a more skilled and technology-oriented workforce, the new S-curve industrial revolution is restructuring the labor market worldwide. The Thai government is now focusing on upgrading the country's human resource skills to meet new demands. This paper presents an application of the well-known A* path planner in the field of artificial intelligence (AI) for recommending reskilling/upskilling training courses. Data are obtained from the Career Discovery Analysis Platform (CDAP), which was designed and implemented by the authors. The results obtained from CDAP are then summarized, leading to training course recommendations for the government and individuals. By considering the mean score zone as the sensing node of a graph-based planner, an optimal path for upskilling training course recommendation can be identified. [ABSTRACT FROM AUTHOR]

Course recommendations are used to help students with different needs to choose courses. However, students' needs are not always determined by their personal interests, they are also influenced by different curriculum settings, different teacher teams and other factors. Current course recommendation methods lack the consideration of complex relational semantic information that affects students' needs, resulting in unsatisfied recommendation. To address this issue, we propose Meta-Relationship Course Recommendation (MRCRec) to enrich the expression of relational information. Focusing on complex semantic information of multi-entity relationship and entity association, we construct creatively the multi-entity relational self-symmetric meta-path (MSMP) and associative relational self-symmetric meta-graph (ASMG), which are referred as meta-relationship (MR). We also design an algorithm of meta-relationship correlation measure (MRCor) to obtain semantic correlational information. Then, we adopt the graph embedding to mine and fuse the latent representations of users and that of courses as user preference and course characteristic, respectively. Finally, we optimize matrix factorization to complete recommended task. Comprehensive experiments are conducted on the MOOCCube dataset and XuetangX dataset. The results show that MRCRec can effectively recommend courses for users. [ABSTRACT FROM AUTHOR]

The exponential development of online learning resources has led to an information overload problem. Therefore, recommender systems play a crucial role in E-learning to provide learners with personalised course recommendations by automatically identifying their preferences. In addition, e-Learning platforms such as MOOCs and LMS have been criticised for their low course completion rates, and one of the primary reasons is that they do not provide personalised course recommendations for users with varying interests. Rapidly locating the courses that users are interested in on enormous e-Learning platforms can have a significant impact on the quality of learning and the dissemination of knowledge to the learner. This paper examines the most prevalent recommendation techniques utilised in E-learning. We examined how to apply Deep Transformer based Ensembled Attention Model (DTEAM) on e-Learning recommendation system in order to achieve personalized course recommendations. The proposed recommendation model uses BERT as its foundation integrated with MLM and Transformers. Predicted course recommendations are more aligned with the interests of users. Our experimental results proved that traditional recommendation algorithms, such as collaborative filtering and item-based filtering are incapable of producing superior results. The consequence of the research can assist students in selecting courses according to their preferences and improve their learning calibre. [ABSTRACT FROM AUTHOR]

In recent years, MOOCs (Massive Open Online Courses) have become popular and the online learning resources are increasing, they are an offered courses by schools and universities, which are accessible to everyone and free of charge on the internet, they offer the possibility to teach a very group of students, in the same course, at the same time, even if they are not in the same location. There are many MOOCs platforms with different characteristics, they contain a huge amount of data, so the learner does not know which course to take and can choose irrelevant MOOCs. Therefore, he will waste the time and also the motivation. Recommender systems give a solution to this problem, they suggest learning resources to learners according to their interests and needs, so learner will be satisfied because he finds an appropriate course. In this paper, we give a systematic literature review of MOOCs recommender systems, based on published papers in the past ten years, between 2012 and 2022. We have selected 123 papers from five databases, IEEE Xplore, Springer Link, Science Direct, Google Scholar and ACM Library. We have divided the data analysis in two parts, the quantitative analysis, and the qualitative analysis. In the quantitative analysis, we have studied first the evolution of papers by year and the distribution of papers on databases by type. Then, in the qualitative analysis, we have based principally on the distribution of papers by the existed areas in MOOCs. We have found that there are six main fields, course recommendation, peer recommender, MOOC provider, video recommendation, learning activities and OER, paid activities recommender system and other papers in various types. A high number of articles have been published in the field of courses, which confirms that this domain is very important and crucial for learners. [ABSTRACT FROM AUTHOR]

In this study, we built a personalized hybrid course recommendation system (PHCRS) that considers students’ interests, abilities and career development. To meet students’ individual needs, we adopted the five most widely used algorithms, including content-based filtering, popularity-based methods, item-based collaborative filtering, user-based collaborative filtering, and score-based methods, to build a PHCRS. First, we collected course syllabi and labeled each course (e.g., knowledge/skills taught, basic/advanced level). Next, we used course labels and students’ past course selections and grades to train five recommendation models. To evaluate the accuracy of the system, we performed experiments with students in the Department of Electrical and Computer Engineering, which provides 1794 courses for 925 students and utilizes the receiver operating characteristic curve (ROC) and normalized discounted cumulative gain (NDCG) as metrics. The results showed that our proposed system can achieve accuracies of 80% for ROC and 90% for NDCG. We invited 46 participants to test our system and complete a questionnaire. Overall, 60 to 70% of participants were interested in the recommended courses, while the course recommendation lists produced by content-based filtering were in line with 67.40% of students’ actual course preferences. This study also found that students were more interested in courses at the top of the recommendation lists, and more students were autonomously motivated than held extrinsic informational motivation across the five recommendation methods. These findings highlighted that the proposed course recommendation system can help students choose the courses that interest them most.

The phenomenon of high dropout rates has been the concern of MOOC providers and educators since the emergence of this disruptive technology in online learning. This led to the focus on learner motivation studies from different aspects like demotivation signs detection, learning path personalization and course recommendation. Our paper aims to predict learner motivation for MOOCs to select the right MOOC for the right learner. Accordingly, we predict the motivation in an educational data mining approach by extracting and preprocessing learners' navigation traces on a MOOC platform, and building a Machine Learning model that predicts accurately a given learner's motivation for a MOOC. The comparison of the performance of four supervised learning algorithms resulted in the selection of the Random Forest classifier as the best modeling technique for motivation prediction with an accuracy of 95%. Afterward, we test the Machine Learning-based recommendation function for learners of the MOOC platform dataset to recommend the Top-10 MOOCs suitable for the target learner. Finally, further research on learner characteristics considered in recommender systems could enlarge the recommendation scope of MOOCs and maintain learner motivation. [ABSTRACT FROM AUTHOR]

Abstract Recommendation systems need a deeper understanding of users and their motivations to improve recommendation quality and provide more personalized suggestions. This is especially true in the education domain, the more about the student is known, the more useful recommendations can be made. However, although many studies on the course recommendation exist, studies on the students’ course selection motivations in universities are limited. This study investigates the factors that contribute to students’ choice when selecting courses in universities to better understand student perceptions, attitudes, and needs and leverage data-driven approaches for recommending and explaining the recommendations in university environments. A qualitative interview for university students (N = 10) comprised of open-ended questions as well as a questionnaire for students (N = 81) was conducted, aiming to investigate the main reasons behind their choices. The results of this study show that students highly value the course contents and the benefits of the course towards their future careers. Furthermore, students are influenced by other reasons such as the possibility of obtaining a higher grade, the popularity of professors, and recommendations from peers. Next, we extract the main categories of students’ motivations and analyzed the questionnaire data by employing statistical analysis methods as well as the k-means clustering algorithm to identify different types of students in terms of course selection. Based on our findings, we discuss implications for designing more personalized course recommendation systems.

Abstract The abundance of courses available in a university often overwhelms students as they must select courses that are relevant to their academic interests and satisfy their requirements. A large number of existing studies in course recommendation systems focus on the accuracy of prediction to show students the most relevant courses with little consideration on interactivity and user perception. However, recent work has highlighted the importance of user-perceived aspects of recommendation systems, such as transparency, controllability, and user satisfaction. This paper introduces CourseQ, an interactive course recommendation system that allows students to explore courses by using a novel visual interface so as to improve transparency and user satisfaction of course recommendations. We describe the design concepts, interactions, and algorithm of the proposed system. A within-subject user study (N=32) was conducted to evaluate our system compared to a baseline interface without the proposed interactive visualization. The evaluation results show that our system improves many user-centric metrics including user acceptance and understanding of the recommendation results. Furthermore, our analysis of user interaction behaviors in the system indicates that CourseQ could help different users with their course-seeking tasks. Our results and discussions highlight the impact of visual and interactive features in course recommendation systems and inform the design of future recommendation systems for higher education.

The expansion of the population that wants to learn online is growing due to several e-learning platforms, which help innovate and suggest courses to learners. Several techniques are devised for determining optimal courses for the learner. In recent days, researchers began to utilize recommendation systems in e-learning. This paper devises a novel technique for course recommendation to students in an e-learning platform, which helps learners select the best course. Here, the Butterfly Weed Optimization (BWO) is newly devised by combining Invasive Weed Optimization (IWO) and Butterfly Optimization Algorithm (BOA). At first, the process is performed by inputting the data to the Course subscription matrix for constructing the matrix based on learner interest and courses. Here, course grouping is performed using Interval type-2 Fuzzy Local Enhancement Based Rough K-means Clustering. Furthermore, the course is matched with input data based on entropy and angular distance. Finally, the sentiment classification is performed using the Ontology-based approach SentiWordNet and Deep Neural Network (DNN). Here, the DNN is trained with the proposed BWO algorithm, and thus the course recommendation is attained by offering a suitable course recommendation to learners. [ABSTRACT FROM AUTHOR]

To provide a good study plan is key to avoid students' failure. Academic advising based on student's preferences, complexity of the semester, or even background knowledge is usually considered to reduce the dropout rate. This article aims to provide a good course index to recommend courses to students based on the sequence of courses already taken by each student. Hence, unlike existing long-term course planning methods, it is based on graduate students to model the course and not on external factors that might introduce some bias in the process. The proposal includes a novel sequential pattern mining algorithm, called (ES) 2 P (Evolutionary Search of Emerging Sequential Patterns), that properly identifies paths followed by good students and not followed by not so good students, as a long-term course planning approach. A major feature of the proposed (ES) 2 P algorithm is its ability to extract the best k solutions, that is, those with a best recommendation index score instead of returning the whole set of solutions above a predefined threshold. A real study case is performed including more than 13,000 students belonging to 13 faculties to demonstrate the usefulness of the proposal not only to recommend study plans but also to give advices at different stages of the students' learning process. [ABSTRACT FROM AUTHOR]