scholarly journals Personalized Hybrid Educational Recommender System Using Matrix Factorization with User and Item Information

2020 ◽  
Author(s):  
Paula Andrea Rodriguez-Marin ◽  
Nestor Dario Duque-Mendez ◽  
Demetrio Arturo Ovalle-Carranza ◽  
Juan David Martinez-Vargas
Keyword(s):  
Learning Style ◽  
Recommender System ◽  
Matrix Factorization ◽  
Educational Resources ◽  
Item Information ◽  
Educational Environments ◽  
Personalized Recommender System ◽  
Online Educational Resources ◽  
The Right ◽  
Available Information

One of the main challenges for autonomous learning in virtual environments is finding the right material that fits students’ needs and supports their learning process. Personalized recommender systems partially solve this problem by suggesting online educational resources to students based on their preferences. However, in educational environments (which need a proper characterization of both users and educational resources), most existing recommendation algorithms either fail to include all the available information or use hybrid processes that do not exploit possible relationships between users and item features. This article presents a personalized recommender system for educational resources aimed at combining user and item information into a single mathematical model based on matrix factorization. As a result, estimated latent factors can provide insight into possible interactions between users and item features, improving the quality of the information retrieval process. We validated the proposed model on a real dataset that contains the ratings assigned by students from Universidad Nacional de Colombia and Universidade Feevale to educational resources in the Colombian Federation of Learning Object Repositories (FROAC in Spanish). User characterization included learning style and educational level, whereas item characterization (obtained from the objects’ metadata), included interactivity level, aggregation level and type, and resource format. These results, compared to those obtained when not all the available information is included, show that our method can improve the recommendation process.

Pre-Filling Collaborative Filtering Algorithm Based on Matrix Factorization

2013 ◽  
Vol 411-414 ◽  
pp. 2223-2228
Author(s):  
Dong Liang Su ◽  
Zhi Ming Cui ◽  
Jian Wu ◽  
Peng Peng Zhao
Keyword(s):  
Collaborative Filtering ◽  
Recommender System ◽  
Matrix Factorization ◽  
Nearest Neighbor ◽  
User Profile ◽  
Personalized Recommendation ◽  
System Quality ◽  
Recommendation Algorithm ◽  
Collaborative Filtering Algorithm ◽  
Personalized Recommender System

Nowadays personalized recommendation algorithm of e-commerce can hardly meet the needs of users as an ever-increasing number of users and items in personalized recommender system has brought about sparsity of user-item rating matrix and the emergence of more and more new users has threatened recommender system quality. This paper puts forward a pre-filled collaborative filtering recommendation algorithm based on matrix factorization, pre-filling user-item matrixes by matrix factorization and building nearest-neighbor models according to new user profile information, thus mitigating the influence of matrix sparsity and new users and improving the accuracy of recommender system. The experimental results suggest that this algorithm is more precise and effective than the traditional one under the condition of extremely sparse user-item rating matrix.

ACCESS TO EDUCATION WITH ONLINE LEARNING AND OPEN EDUCATIONAL RESOURCES: CAN THEY CLOSE THE GAP?

2008 ◽  
Vol 12 (1) ◽  
Author(s):  
Christine Geith ◽  
Karen Vignare
Keyword(s):  
Online Learning ◽  
Global Education ◽  
Open Educational Resources ◽  
Educational Resources ◽  
Access To Education ◽  
Human Beings ◽  
Right To Education ◽  
Education Gap ◽  
The Right ◽  
Compare And Contrast

One of the key concepts in the right to education is access: access to the means to fully develop as human beings as well as access to the means to gain skills, knowledge and credentials. This is an important perspective through which to examine the solutions to access enabled by Open Educational Resources (OER) and online learning. The authors compare and contrast OER and online learning and their potential for addressing human rights “to” and “in” education. The authors examine OER and online learning growth and financial sustainability and discuss potential scenarios to address the global education gap.

Toward a Hybrid Recommender System for E-learning Personnalization Based on Data Mining Techniques

2018 ◽  
Vol 2 (4) ◽  
pp. 271 ◽  
Author(s):  
Outmane Bourkoukou ◽  
Essaid El Bachari
Keyword(s):  
Learning Style ◽  
Recommender System ◽  
Adaptive Learning ◽  
Learning Objects ◽  
Research Field ◽  
Learning System ◽  
K Nearest Neighbors ◽  
E Learning ◽  
Hybrid Recommender System ◽  
Hybrid Recommender

Personalized courseware authoring based on recommender system, which is the process of automatic learning objects selecting and sequencing, is recognized as one of the most interesting research field in intelligent web-based education. Since the learner’s profile of each learner is different from one to another, we must fit learning to the different needs of learners. In fact from the knowledge of the learner’s profile, it is easier to recommend a suitable set of learning objects to enhance the learning process. In this paper we describe a new adaptive learning system-LearnFitII, which can automatically adapt to the dynamic preferences of learners. This system recognizes different patterns of learning style and learners’ habits through testing the psychological model of learners and mining their server logs. Firstly, the device proposed a personalized learning scenario to deal with the cold start problem by using the Felder and Silverman’s model. Next, it analyzes the habits and the preferences of the learners through mining the information about learners’ actions and interactions. Finally, the learning scenario is revisited and updated using hybrid recommender system based on K-Nearest Neighbors and association rule mining algorithms. The results of the system tested in real environments show that considering the learner’s preferences increases learning quality and satisfies the learner.

scholarly journals Movie Recommendation through Multiple Bias Analysis

2021 ◽  
Vol 11 (6) ◽  
pp. 2817
Author(s):  
Tae-Gyu Hwang ◽  
Sung Kwon Kim
Keyword(s):  
Decision Making ◽  
Recommender System ◽  
Real World ◽  
Matrix Factorization ◽  
User Preferences ◽  
Improve Performance ◽  
Bias Analysis ◽  
Useful Knowledge ◽  
Existing Problems ◽  
Movie Recommendation

A recommender system (RS) refers to an agent that recommends items that are suitable for users, and it is implemented through collaborative filtering (CF). CF has a limitation in improving the accuracy of recommendations based on matrix factorization (MF). Therefore, a new method is required for analyzing preference patterns, which could not be derived by existing studies. This study aimed at solving the existing problems through bias analysis. By analyzing users’ and items’ biases of user preferences, the bias-based predictor (BBP) was developed and shown to outperform memory-based CF. In this paper, in order to enhance BBP, multiple bias analysis (MBA) was proposed to efficiently reflect the decision-making in real world. The experimental results using movie data revealed that MBA enhanced BBP accuracy, and that the hybrid models outperformed MF and SVD++. Based on this result, MBA is expected to improve performance when used as a system in related studies and provide useful knowledge in any areas that need features that can represent users.

MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health

2020 ◽  
Author(s):  
Darius A. Rohani ◽  
Andrea Quemada Lopategui ◽  
Nanna Tuxen ◽  
Maria Faurholt-Jepsen ◽  
Lars V. Kessing ◽  
...  
Keyword(s):  
Mental Health ◽  
Recommender System ◽  
Behavioral Activation ◽  
Personalized Recommender System

scholarly journals The value of urban trails, statuary and installations for Geoscience education: uses and abuses from the north of England and further afield

2018 ◽  
Vol 14 (3) ◽  
pp. 277-281
Author(s):  
Phillip J. Murphy ◽  
Elizabeth Murphy
Keyword(s):  
Building Stone ◽  
Educational Resources ◽  
Geoscience Education ◽  
Web Based ◽  
The North ◽  
Geological Maps ◽  
Geological Map ◽  
The Right ◽  
Education Resource ◽  
City Park

The origins, uses and fates of a number of purpose built urban educational resources sited in the north of England are reviewed. These include walk on geological maps, building stone trails, a church gate and landscaping in a city park. A geological trail in the municipal cemetery of Rochdale dating from 1855 is a candidate for the oldest purpose made geological education trail in the world and the most recent educational resource was built in 2015. The destruction of a walk on geological map of England and Wales in 2004 shows that such valuable geoscience educational resources are in need of protection. A range of educational uses of these resources are suggested. Comparison is made with similar resources in London, both statuary and web based, and ways to ensure their preservation and continued educational use are suggested. This study shows that a geoscience education resource, if sited in the right place and looked after, can be an exciting and inspirational education resource in regular use for over half a century.

Sign in / Sign up

Export Citation Format

Share Document