Recommendation System based on user interaction data applied to intelligent electronic books

Crespo, Rubén González; Martínez, Óscar Sanjuán; Lovelle, Juan Manuel Cueva; García-Bustelo, B. Cristina Pelayo; Gayo, José Emilio Labra; Pablos, Patricia Ordóñez de

doi:10.1016/j.chb.2010.09.012

Cited by 69 publications

(21 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, the few studies have implemented the ebook systems with personalized interactions and recommendations in order to enhance students' learning with e-books [8,10]. An e-book system developed by Crespo and his colleagues [10] has been provided with the personalized recommendation solutions to help the users choose objects which are useful and suitable for them.…”

Section: Related Workmentioning

confidence: 99%

“…An e-book system developed by Crespo and his colleagues [10] has been provided with the personalized recommendation solutions to help the users choose objects which are useful and suitable for them. The results of their study showed that their system could be used efficiently to solve the problem of information overload as well as could improve the user experience by providing recommendations automatically.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Framework of Teaching and Learning with e-Textbooks in Smart Learning Environment

Fan

Chang

Huang

et al. 2015

2015 IEEE 15th International Conference on Advanced Learning Technologies

View full text Add to dashboard Cite

Technology in education has caused numerous of changes. The use of electronic books (e-books) is one of these changes; however, it is given the slower than expected growth. In other words, there is few complete consideration for using ebooks materials into education. Therefore, this study proposes a framework to consider how to transfer the traditional textbooks into electronic textbooks called e-textbooks. Then, this framework also considers how to apply these e-textbooks into the classroom and individual learning in order to create a smart learning environment for teachers and students. This smart learning environment can offer not only rich interactive multimedia via tablets but also provide personalized adaptivity to each student. This study also takes the outcomes of our previous studies into account to provide content providers, teachers, and students with the suitable and appropriate etextbook systems. 1

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Framework of Teaching and Learning with e-Textbooks in Smart Learning Environment

Fan

Chang

Huang

et al. 2015

2015 IEEE 15th International Conference on Advanced Learning Technologies

View full text Add to dashboard Cite

show abstract

“…Therefore, it is significant to filter unrelated information and provide personalized recommendations to meet the manifold needs of the people. Nowdays, recommender system [1,2] has become the essential tool for online life. Many e-commerce websites rely on the recommender system to suggest consumers new possibly relevant items, e.g.…”

Section: Introductionmentioning

confidence: 99%

Predictability of diffusion-based recommender systems

Zhang

Xue

Zeng

2019

Knowledge-Based Systems

View full text Add to dashboard Cite

The recommendation methods based on network diffusion have been shown to perform well in both recommendation accuracy and diversity. Nowdays, numerous extensions have been made to further improve the performance of such methods. However, to what extent can items be predicted by diffusion-based algorithms still lack of understanding. Here, we mainly propose a method to quantify the predictability of diffusion-based algorithms. Accordingly, we conduct experiments on Movielens and Netflix datasets. The results show that the higher recommendation accuracy based on diffusion algorithms can still be achieved by optimizing the way of resource allocation on a density network. On a sparse network, the possibility of improving accuracy is relatively low due to the fact that the current accuracy of diffusion-based methods is very close its predictability. In this case, we find that the predictability can be improved significantly by multi-steps diffusion, especially for users with less historical information. In contrast to common belief, there are plausible circumstances where the higher predictability of diffusion-based methods do not correspond to those users with more historical recording. Thus, we proposed the diffusion coverage and item average degree to explain this phenomenon. In addition, we demonstrate the recommendation accuracy in real online system is overestimated by random partition used in the literature, suggesting the recommendation in real online system may be a harder task.

show abstract

“…A recommender system suggests the relevant content to its users on the basis of his past preferences or preferences of his community [44]. Log files of the web-servers contain useful information regarding user's access to the website or web application.…”

Section: Recommendation Enginementioning

confidence: 99%

An Intelligent Service-Based Layered Architecture for eLearning and eAssessment

Javaid¹,

Arif²,

Talpur³

et al. 2017

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

The rapid advancement in ICT (Information & Communication Technology) is causing a paradigm shift in eLearning domain. Traditional eLearning systems suffer from certain shortcomings like tight coupling of system components, lack of personalization, flexibility, and scalability and performance issues. This study aims at addressing these challenges through an MAS (Multi Agent System) based multi-layer architecture supported by web services. The foremost objective of this study is to enhance learning process efficiency by provision of flexibility features for learning and assessment processes. Proposed architecture consists of two sub-system namely eLearning and eAssesssment. This architecture comprises of five distinct layers for each sub-system, with active agents responsible for miscellaneous tasks including content handling, updating, resource optimization, load handling and provision of customized environments for learners and instructors. Our proposed architecture aims at establishment of a facilitation level to learners as well as instructors for convenient acquisition and dissemination of knowledge. Personalization features like customized environments, personalized content retrieval and recommendations, adaptive assessment and reduced response time, are believed to significantly enhance learning and tutoring experience. In essence characteristics like intelligence, personalization, interactivity, usability, laidback accessibility and security, signify aptness of proposed architecture for improving conventional learning and assessment processes. Finally we have evaluated our proposed architecture by means of analytical comparison and survey considering certain quality attributes.Key Words: E-Learning, E-Assessment, Architecture, Data Mining, Intelligent Agent. Section 2 provides related work in areas of MAS, SOA, personalized leaning and query processing. Section 3 provides general architecture with detailed description of the proposed system and underlying layers. Section 4 provides evaluations mechanism followed by conclusion in section 5. RELATED WORDMAS is a sub-discipline of DAI (Distributed Artificial Intelligence

show abstract

Recommendation System based on user interaction data applied to intelligent electronic books

Cited by 69 publications

References 3 publications

A Framework of Teaching and Learning with e-Textbooks in Smart Learning Environment

A Framework of Teaching and Learning with e-Textbooks in Smart Learning Environment

Predictability of diffusion-based recommender systems

An Intelligent Service-Based Layered Architecture for eLearning and eAssessment

Contact Info

Product

Resources

About