Learning path recommendation based on modified variable length genetic algorithm

Dwivedi, Pragya; Kant, Vibhor; Bharadwaj, Kamal Kant

doi:10.1007/s10639-017-9637-7

Cited by 110 publications

(76 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Considering the educational context and its inherent diversity of search and optimization problems, the use of bio-inspired evolutionary algorithms to seek for solutions and solve optimization problems is an interesting strategy to support personalized recommendation of LOs [Bhaskaran and Santhi 2017, Kurilovas et al 2014, Dwivedi et al 2018. According to [Krishnanand et al 2009], bio-inspired evolutionary algorithms are probabilistic search methods that simulate the evolution or the behavior 2 http://dbpedia.org/sparql IX Congresso Brasileiro de Informática na Educação (CBIE 2020) Anais do XXXI Simpósio Brasileiro de Informática na Educação (SBIE 2020) of biological entities.…”

Section: Background and Related Workmentioning

confidence: 99%

Personalized Recommendation of Learning Objects Through Bio-inspired Algorithms and Semantic Web Technologies: an Experimental Analysis

Júnior¹,

Júnior²,

Araújo³

et al. 2020

Anais Do XXXI Simpósio Brasileiro De Informática Na Educação (SBIE 2020)

View full text Add to dashboard Cite

The emerging need to explore the Web as a learning source allied with the purpose of providing personalized recommendations is a tough task. Considering this scenario, this work presents an approach that combines Semantic Web technologies and bio-inspired algorithms to perform personalized recommendation of Learning Objects (LOs) using local repositories and Web resources. Web resources are retrieved and structured as LOs, which allows for the automatic generation of metadata, minimizing course tutors' work. Experiments were performed to verify which bio-inspired evolutionary algorithm would be most appropriate in this context. Also, discussions regarding the quality of recommendations considering local repositories and Web have been made. Initial experiments evaluating the efficiency of the proposed approach have shown promising results.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Personalized Recommendation of Learning Objects Through Bio-inspired Algorithms and Semantic Web Technologies: an Experimental Analysis

Júnior¹,

Júnior²,

Araújo³

et al. 2020

Anais Do XXXI Simpósio Brasileiro De Informática Na Educação (SBIE 2020)

View full text Add to dashboard Cite

show abstract

“…Recently, [21] relied on deep learning, precisely LSTM associated with clustering. [3] focused on students learning styles and knowledge levels with a variable length genetic algorithm to recommend personalised LPs. Few years ago, Bayes theorem, Association Link Network, Item Response Theory, graph theory were studied to form and recommend LPs.…”

Section: Learning Path Recommender Systemsmentioning

confidence: 99%

New Measures for Offline Evaluation of Learning Path Recommenders

Zhang

Brun

Boyer

2020

Addressing Global Challenges and Quality Education

View full text Add to dashboard Cite

Recommending students useful and effective learning paths is highly valuable to improve their learning experience. The evaluation of the effectiveness of this recommendation is a challenging task that can be performed online or offline. Online evaluation is highly popular but it relies on actual path recommendations to students, which may have dramatic implications. Offline evaluation relies on static datasets of students' learning activities and simulates paths recommendations. Although easier to run, it is difficult to accurately evaluate offline the effectiveness of a learning path recommendation. To tackle this issue, this work proposes simple offline evaluation measures. We show that they actually allow to characterise and differentiate the algorithms.

show abstract

“…However, other approaches are based on previous knowledge www.ijacsa.thesai.org and log file of online activities [1]; therefore, the seminar taken adequately by learner interacts with individual preference [1]. The reference [2] proposed a genetic algorithm to sequence learning path based on learner preferences. Learning analytics provides tools for collecting analyzing data about learners to optimize learning.…”

Section: Learning Pathsmentioning

confidence: 99%

Effective Framework of Pedagogy

Naz¹,

Khan²,

Mahmood³

2019

IJACSA

View full text Add to dashboard Cite

Learning paths drive learners to proficiency by using a selected sequence of training activities under time constraints. Therefore, learners can regulate learning and give feedback for pedagogy improvements. Studying learning path evaluation provides a useful conceptual reference to enhance pedagogically. This paper proposes an approach based on the Plan-Do-Check-Act improvement cycle to systematically evaluate learning paths in learning management systems. The framework is a valuable resource that consolidates existing practices in learning management evaluation. Our approach integrates learning styles, learning profile, along with cognitive activities. The proposed framework was compared with current learning path methods. Results were competitive compared with related works.

show abstract

Learning path recommendation based on modified variable length genetic algorithm

Cited by 110 publications

References 35 publications

Personalized Recommendation of Learning Objects Through Bio-inspired Algorithms and Semantic Web Technologies: an Experimental Analysis

Personalized Recommendation of Learning Objects Through Bio-inspired Algorithms and Semantic Web Technologies: an Experimental Analysis

New Measures for Offline Evaluation of Learning Path Recommenders

Effective Framework of Pedagogy

Contact Info

Product

Resources

About