Semantic Classification and Indexing of Open Educational Resources with Word Embeddings and Ontologies

Koutsomitropoulos, Dimitrios A.; Andriopoulos, Andreas D.; Likothanassis, Spiridon D.

doi:10.2478/cait-2020-0043

Cited by 7 publications

(6 citation statements)

References 24 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Niu et al [23] proposed a novel theory of semantic cohesion for Chinese airworthiness regulations and specified four critical elements of the theory, namely, definition, model, theorem, and rules. Koutsomitropoulos et al [24] combined explicit knowledge graph representations with vector-based learning of formal thesaurus terms into a hybrid semantic classification model and demonstrated the good effect of the hybrid model on the classification of biological files in library terminology learning. With the aid of the enhanced learning model, Shen and Ho [25] evaluated HE teaching effects and quickly grasped the development state of HE.…”

Section: Literature Reviewmentioning

confidence: 99%

Semantic-Based Classification of Long Texts on Higher Education in China

Chun¹,

Fei²

2021

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

The development level of higher education (HE) is an important indicator of the development level and development potential of a country. The HE-related document is the mirror to reflect the develop process of the HE. The research of high education (HE) has been developing rapidly in China, resulting in a huge number of texts, such as relevant policies, speech drafts, and yearbooks. The traditional manual classification of HE texts is inefficient and unable to deal with the huge number of HE texts. Besides, the effect of direct classification is rather poor because HE texts tend to be long and exist as an imbalanced dataset. To solve these problems, this paper improves the convolutional neural network (CNN) into the HE-CNN classification model for HE texts. Firstly, Chinese HE policies, speech drafts, and yearbooks (1979–2020) were downloaded from the official website of Chinese Ministry of Education. In total, 463 files were collected and divided into four classes, namely, definition, task, method, and effect evaluation. To handle the huge number of HE texts, the Twitter-latent Dirichlet allocation (LDA) topic model was employed to extract word frequency and critical information, such as age and author, enhancing the training effect of CNN. To address the dataset imbalance problem, CNN parameters were optimized repeatedly through comparative experiments, which further improve the training effect. Finally, the proposed HE-CNN model was found more effective and accurate than other classification models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Semantic-Based Classification of Long Texts on Higher Education in China

Chun¹,

Fei²

2021

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

show abstract

“…In the first case, we rely on the cosine distance to determine the semantic similarity between the embeddings produced by the model and the various MeSH terms. The idea of thresholding has been thoroughly investigated previously by the authors [ 13 ]. By considering a certain similarity threshold above which values are classified as positive, we can improve the quality of thematic suggestions.…”

Section: Classification Methodologymentioning

confidence: 99%

Thesaurus-based word embeddings for automated biomedical literature classification

Koutsomitropoulos

Andriopoulos

2021

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

The special nature, volume and broadness of biomedical literature pose barriers for automated classification methods. On the other hand, manually indexing is time-consuming, costly and error prone. We argue that current word embedding algorithms can be efficiently used to support the task of biomedical text classification even in a multilabel setting, with many distinct labels. The ontology representation of Medical Subject Headings provides machine-readable labels and specifies the dimensionality of the problem space. Both deep- and shallow network approaches are implemented. Predictions are determined by the similarity between extracted features from contextualized representations of abstracts and headings. The addition of a separate classifier for transfer learning is also proposed and evaluated. Large datasets of biomedical citations are harvested for their metadata and used for training and testing. These automated approaches are still far from entirely substituting human experts, yet they can be useful as a mechanism for validation and recommendation. Dataset balancing, distributed processing and training parallelization in GPUs, all play an important part regarding the effectiveness and performance of proposed methods.

show abstract

“…OER Recommenders for teachers or could be adopted for teaching purposes [34], [35], [36], [17], [37], [31], [20], [36], [22], [39], [24], [25], [26] [27], [40], [29], [41], [42], [43], [44], [45], [46], [47], [31], [48], [49], [50], [51], [52], [53], [54], [124], [125], [128], [130] Generalities Literature reviews, SLR, surveys,, [63], [64], [65], [66] , [67], [68], [69], [70], [71], [72], [73], [74], [75], [76], [77],…”

Section: Figmentioning

confidence: 99%

Systematic Literature Review on Open Educational Resources Recommender Systems

Rima

Meriem²,

Ajhoun³

2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

background: In recent years, recommender systems (RS) have grown in popularity among learning and education stakeholders, while open educational resources (OER) have begun to be deployed to improve the education field. The selection of OERs should not be haphazard; rather, it should be based on the learning objectives and (RS) commonly utilized to overcome the abundance of OER. Objective: The aim of this paper is to examine the current advances in OER recommenders and the different commonly used recommendation approaches and technical features, to position our future research alongside the existing. Method: A systematic literature review with a deductive approach using the grounded theory technique, combining quantitative and qualitative analysis by adopting open coding (inductive and deductive) for content analysis. Databases: we employed Google Scholar as a search engine to crawl data. Results: The findings are presented according to the (Bernard, H. Russell .2000) process. We present the results of the analysis using quotes from interviews that illuminate the theory (exemplars). Conclusion: The review reveals an emerging interest in the area; nevertheless, hybrid interactive systems; chatbot-based, dedicated to course creators are lacking. Further and future research is needed

show abstract

Semantic Classification and Indexing of Open Educational Resources with Word Embeddings and Ontologies

Cited by 7 publications

References 24 publications

Semantic-Based Classification of Long Texts on Higher Education in China

Semantic-Based Classification of Long Texts on Higher Education in China

Thesaurus-based word embeddings for automated biomedical literature classification

Systematic Literature Review on Open Educational Resources Recommender Systems

Contact Info

Product

Resources

About