Discover learning path for group users: A profile-based approach

Xie, Haoran; Zou, Di; Wang, Fu Lee; Wong, Tak‐Lam; Rao, Yanghui; Wang, Simon Ho

doi:10.1016/j.neucom.2016.08.133

Cited by 47 publications

(25 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The main advantage of this approach is that it is easy to implement and the measure is very simple as it does not require additional elements However, from our point of view, the fact that the second group gets recommendations (non personalised) introduces a bias in the evaluation. [20] went a step further in the evaluation approach. The students' performance is not only compared between groups, but their performance before and after adopting a LP is also considered.…”

Section: Online Evaluation Of Lp Recommendationsmentioning

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

Section: Online Evaluation Of Lp Recommendationsmentioning

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

show abstract

“…However, their model fails to predict rating for cold start item when there is no rating available for newly coming item in any of the available user rating profiles. A profile based framework for learning path discovery is proposed in [28] which assists the group of learners to acquire new knowledge. Their proposed group model reflects the characteristics and values of group learners which helps to identify a suitable learning path in an e-learning environment.…”

Section: Related Workmentioning

confidence: 99%

HRS-CE: A hybrid framework to integrate content embeddings in recommender systems for cold start items

Anwaar

Iltaf

Afzal

et al. 2018

Journal of Computational Science

View full text Add to dashboard Cite

Recommender systems (RSs) provide the personalized recommendations to users for specific items in a wide range of applications such as e-commerce, media recommendations and social networking applications. Collaborative Filtering (CF) and Content Based (CB) Filtering are two methods which have been employed in implementing the recommender systems. CF suffers from Cold Start (CS) problem where no rating records (Complete Cold Start CSS) or very few records (Incomplete Cold Start ICS) are available for newly coming users and items. The performance of CB methods relies on good feature extraction methods so that the item descriptions can be used to measure items similarity as well as for user profiling. This paper addresses the CS problem by providing a novel way of integrating content embeddings in CF. The proposed algorithm (HRS-CE) generates the user profiles that depict the type of content in which a particular user is interested. The word embedding model (Word2Vec) is used to produce distributed representation of items descriptions. The higher representation for an item description, obtained using content embeddings, are combined with similarity techniques to perform rating predictions. The proposed method is evaluated on two public benchmark datasets (MovieLens 100k and MovieLens 20M). The results demonstrate that the proposed model outperforms the state of the art recommender system models for CS items.

show abstract

“…A tarefa de definir caminhos de aprendizagem torna-se difícil, devido à complexidade na qual as características e condições iniciais do grupo interagem entre si [Xie et al 2017]. Um caminho de aprendizagem inadequado, quando atribuído à um indivíduo, pode levar a consequências negativas [Xie et al 2017], tais como: falta de interesse, atraso na entrega da atividade e má formação de competências [Cardoso et al 2016, Belacel et al 2014.…”

Section: Contexto Do Problemaunclassified

“…Um caminho de aprendizagem inadequado, quando atribuído à um indivíduo, pode levar a consequências negativas [Xie et al 2017], tais como: falta de interesse, atraso na entrega da atividade e má formação de competências [Cardoso et al 2016, Belacel et al 2014. Embora seja um problema da área de educação, abordagens computacionais têm sido desenvolvidas e aplicadas neste contexto.…”

Section: Contexto Do Problemaunclassified

See 1 more Smart Citation

Seleção de Caminho de Aprendizagem para Grupo de Usuários: Uma Abordagem baseada em Perfil

Miranda

Ferreira

Fiorentino

et al. 2017

Anais Do XXVIII Simpósio Brasileiro De Informática Na Educação (SBIE 2017)

View full text Add to dashboard Cite

Abstract. Identifying learning paths is a key issue for effective learning. This article proposes an intelligent method to optimize the process of selection of learning paths for a group of individuals taking into account multiple criteria: satisfaction of the team members and time spent in the accomplishment of the activity. The method was evaluated regarding the performance, being compared to the exhaustive and random approaches; And regarding the pedagogical aspect, being compared with random and self-selected methods. The results showed the potential of the proposed method from the computational point of view as well as the pedagogical point of view.Resumo. A identificação de caminhos de aprendizagem é uma questão chave para a aprendizagem eficiente. Este artigo propõe um método inteligente para otimizar o processo de seleção de caminhos de aprendizagem para um grupo de indivíduos, levando em conta múltiplos critérios: satisfação dos membros da equipe e tempo gastos na realização da atividade. O método foi avaliado quanto ao desempenho, sendo comparado às abordagens exaustiva e aleatória; e quanto ao aspecto pedagógico, sendo comparado com os métodos aleatório e auto-selecionado. Os resultados obtidos mostraram o potencial do método proposto tanto do ponto de vista computacional quanto do pedagógico. IntroduçãoOs recentes avanços no campo da e-learning possibilitaram a utilização de ambientes virtuais para alcançar estudantes sem limites espaciais e temporais [Voss et al. 2013]. No entanto, ainda existem dificuldades enfrentadas nesses ambientes como: falta de motivação dos alunos, acompanhamento individual do professor para a grande quantidade de estudantes e utilização de todos os recursos disponíveis. Um dos motivos para esses problemas ocorrerem é que a aprendizagem não se dá apenas através da disponibilização de recursos de aprendizagem, mas também da identificação de caminhos de aprendizagem interessantes para cada estudante [dos Santos et al. 2015].Um Caminho de aprendizagem é um conjunto de unidades de aprendizagem (por exemplo, materiais de estudo) que determina o caminho pelo qual o aluno deve seguir, em termos de conhecimento a ser adquirido ou aperfeiçoado, para que o mesmo realize tarefas relacionadas a essas competências [Li et al. 2009]. Em muitas situações, alunos

show abstract

Discover learning path for group users: A profile-based approach

Cited by 47 publications

References 25 publications

New Measures for Offline Evaluation of Learning Path Recommenders

New Measures for Offline Evaluation of Learning Path Recommenders

HRS-CE: A hybrid framework to integrate content embeddings in recommender systems for cold start items

Seleção de Caminho de Aprendizagem para Grupo de Usuários: Uma Abordagem baseada em Perfil

Contact Info

Product

Resources

About