Application of context-aware and personalized recommendation to implement an adaptive ubiquitous learning system

Wang, Shulin; Wu, Chang-Luen

doi:10.1016/j.eswa.2011.02.083

Cited by 148 publications

(65 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wang & Wu applied context aware technology and recommendation algorithms to develop a u-learning system to help lifelong learning learners realize personalized learning goals in a context aware manner and improve the learner's learning effectiveness [3]. In fact, they established that when integrating the relevant information technology to develop a u-learning environment, it is necessary to consider the personalization requirements of the learner to ensure that the technology achieves its intended result.…”

Section: Related Workmentioning

confidence: 99%

“…As defined in [3] context-aware ubiquitous learning is an innovative approach that integrates wireless, mobile, and context-awareness technologies to detect the situation of learners in the real world and thus provide adaptive support, personalized services or guidance accordingly. In the traditional e-learning environments [4] the lack of immediate learning assistance means the learner is unable to receive learning resources in a timely manner and incorporate them based on the actual context into the learner's learning activities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive and Personalized Educational Ubiquitous Multi-Agent System Using Context-Awareness Services and Mobile Devices

Salazar

Ovalle

Duque

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In the last decade, some useful contributions have occurred to elearning system development such as adaptation, ubiquity, personalization, as well as context-awareness services. The aim of this paper is to present the advantages brought by the integration of ubiquitous computing along with distributed artificial intelligence techniques in order to build an adaptive and personalized context-aware learning system by using mobile devices. Based on this model we propose a multi-agent context-aware u-learning system that offers several functionalities such as context-aware learning planning, personalized course evaluation, selection of learning objects according to student profile, search of learning objects in repository federations, search of thematic learning assistants, and access of current context-aware collaborative learning activities involved. In addition, several context-awareness services are incorporated within the adaptive e-learning system that can be used from mobile devices. In order to validate the model a prototype was built and tested through a case study. Results obtained demonstrate the effectiveness of using this kind of approaches in virtual learning environments which constitutes an attempt to improve learning processes.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive and Personalized Educational Ubiquitous Multi-Agent System Using Context-Awareness Services and Mobile Devices

Salazar

Ovalle

Duque

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…• Adaptive u-learning system [84]: provides context awareness and courseware recommendation functions to enhance lifelong learners' effectiveness to complete their learning task more quickly and more accurately to achieve personal goals.…”

Section: Conceptual and Empirical Workmentioning

confidence: 99%

A Revision of the Literature Concerned with Mobile, Ubiquitous, and Pervasive Learning: A Survey

Peña-Ayala

Cárdenas

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This chapter tailors a perspective of the work fulfilled in three learning research lines, which besides holding many common attributes also tend to converge to shape mobile, ubiquitous, and pervasive sceneries. Such a junction pursues to spread the traditional classroom and distance settings to open environments, as well as use the surrounding physical and digital objects as learning content that is available to learners at anytime, anywhere, and in any way. In sum, a complete learning environment is recreated to provide formal and informal learning to support academic studies, professional training, and lifelong learning. Thus, in this chapter a description of the mobile, ubiquitous, and pervasive learning (MUP-Learning) arena is presented through the selection of a sample of recent and transcendent works that offer from a conceptual contribution, such as models and frameworks, even empirical approaches oriented to specific domains of study. The sample of works is characterized according to a proposed pattern, as well as organized according to a suggested taxonomy. A profile to describe each work is also stated and a series of statistics are presented, as well as an analysis of the arena is provided to understand the potential and challenges related to the MUP-Learning field.

show abstract

“…To solve this problem, numerous methods have been proposed: from information indexing tools, portals, search engine to recommender system which is the most potential one. Recommender systems can do the statistical analysis on users' historical activity records, tap the users' preferences, then automatically find the matching content from the mass of information and make right recommendation [2,3,4]. Nevertheless, the mainstream of recommender systems are troubled by cold start issue.…”

Section: Introductionmentioning

confidence: 99%

A Semi-supervised Solution for Cold Start Issue on Recommender Systems

Zhang

Cheng

Cai

et al. 2015

Web Technologies and Applications

View full text Add to dashboard Cite

Abstract. The recommender system is the most competitive solution to solve information overload problem, and has been extensively applied. The current collaborative filtering based recommender systems explore users' latent interest with their historical online behavior records. They are all facing the cold start issue. In this work, we proposed a background-based semi-supervised tritraining method named BSTM to tackle this problem. In detail, we capture finegrained users' background information by using a factorization model. By exploring these information, the performance of our recommendation can be significantly promoted. Besides, we proposed a semi-supervised ensemble algorithm, which got both labeled and unlabeled data involved. This algorithm assembled diverse weak prediction models which are generated by exploring samples with diverse background information and by tri-training tactic. The experimental results show that, with this solution, the accuracy of recommendation is significantly improved, and the cold-start issue is alleviated.

show abstract

Application of context-aware and personalized recommendation to implement an adaptive ubiquitous learning system

Cited by 148 publications

References 32 publications

Adaptive and Personalized Educational Ubiquitous Multi-Agent System Using Context-Awareness Services and Mobile Devices

Adaptive and Personalized Educational Ubiquitous Multi-Agent System Using Context-Awareness Services and Mobile Devices

A Revision of the Literature Concerned with Mobile, Ubiquitous, and Pervasive Learning: A Survey

A Semi-supervised Solution for Cold Start Issue on Recommender Systems

Contact Info

Product

Resources

About