Supporting Online Video Learning with Concept Map-based Recommendation of Learning Path

Tang, Chien-Lin; Liao, Jingxian; Wang, Hao-Chuan; Sung, Ching-Ying; Cao, Yu-Rong; Lin, Wen‐Chieh

doi:10.1145/3334480.3382943

Cited by 9 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An important factor here was that they identified that TextBlob was unable to read tokenized special characters as a limitation of the module, and factored this into their analysis. Tang et al (2020) adopted the TextBlob sentiment software within their ConceptGuide system. The sentiment analysis here played a crucial element in the evaluation of their tool and future work proposes a learning efficiency analysis that may use similar principles, exemplifying the utilisation of TextBlob outside of a social media context.…”

Section: Related Workmentioning

confidence: 99%

“…Cases of interest include research by Hu, Chancellor & De Choudhury (2019) into discourses relating to homelessness on social media, where topic modelling techniques were deployed to investigate common thematic threads between those who identify as homeless and those who do not. Sentiment analysis and emotion detection techniques have been explored by Tang et al (2020) and Wang et al (2021) , who both used them to garner greater insights into discourses relating to online and remote education.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Critical reflections on three popular computational linguistic approaches to examine Twitter discourses

Heaton

Clos

Nichele

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Although computational linguistic methods—such as topic modelling, sentiment analysis and emotion detection—can provide social media researchers with insights into online public discourses, it is not inherent as to how these methods should be used, with a lack of transparent instructions on how to apply them in a critical way. There is a growing body of work focusing on the strengths and shortcomings of these methods. Through applying best practices for using these methods within the literature, we focus on setting expectations, presenting trajectories, examining with context and critically reflecting on the diachronic Twitter discourse of two case studies: the longitudinal discourse of the NHS Covid-19 digital contact-tracing app and the snapshot discourse of the Ofqual A Level grade calculation algorithm, both related to the UK. We identified difficulties in interpretation and potential application in all three of the approaches. Other shortcomings, such the detection of negation and sarcasm, were also found. We discuss the need for further transparency of these methods for diachronic social media researchers, including the potential for combining these approaches with qualitative ones—such as corpus linguistics and critical discourse analysis—in a more formal framework.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Critical reflections on three popular computational linguistic approaches to examine Twitter discourses

Heaton

Clos

Nichele

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Research on learning path recommendation is mostly based on the idea of constructing a knowledge model from a graph [18,19]. The graph could be a concept map [9,21,22], knowledge map [10,23], ontology [24], topic map [25], or knowledge graph [26][27][28]. The nodes represent the learning content, while the directed edges represent the relationship between the nodes.…”

Section: Related Workmentioning

confidence: 99%

Personalized Learning Path Recommendation Based on Weak Concept Mining

Diao

Zeng

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

Discovering valuable learning path patterns from learner online learning data can provide follow-up learners with effective learning path reference and improve their learning experience and learning effects. In this paper, a personalized learning path recommendation method based on weak concept mining is proposed. Firstly, according to the degree of concept mastery of historical learners, concept maps of different types of learners are generated by clustering and association rule mining algorithms. A set of weak concept learning paths are then automatically generated through topological sorting algorithm. Secondly, the long short-term memory neural network based on the attention mechanism (LSTM+attention) is trained to predict the learning effect of the weak concept learning path. Finally, the personalized weak concept path that meets the expected learning effect is selected from the path prediction results. In the experiment, the proposed method is not only compared with the traditional recommendation method, but also, a comparative experiment on the impact of different learning effect prediction models is carried out. The experiment results show that our proposed method has obvious advantages in recommendation performance.

show abstract

“…It mainly constitutes of two things: concepts and their relationship. In a graph,

G

G ϵ (u, v)

, where

u

are nodes that denote concepts and

v

are edges that denotes the relationship between concepts (Falke et al, 2017; Tang et al, 2021). Here, in this research, concepts are the biomedical domain's neighbouring words and edges represent the semantic similarity between various concepts.…”

Section: Preliminariesmentioning

confidence: 99%

Extractive summarization using concept‐space and keyword phrase

2022

View full text Add to dashboard Cite

PROBLEM: Text summarization is widely used to extract relevant information from documents. The extensive unstructured data are generated in various domains, developing a concise and coherent form of information has become an inevitable and assertive problem among the research community. Automatic text summarization plays a crucial role in acquiring potent knowledge effectively and efficiently for each domain of information. Medical data contains crucial information regarding human diseases and their symptoms. The proposed method will benefit the research community and health experts as it saves a lot of time and resources to compute the patients' summary during diagnosis. APPROACH: In this research, an unsupervised approach is proposed for extractive summarization, based on semantic similarity and keyword-phrase extraction. Merging Concept Map and the RAKE method, a generic summary is computed based on threshold values. Both single-document and multi-document summarization can be accomplished with the approach. RESULTS: To evaluate the proposed unsupervised approach, various biomedical transcripts of neuro-science, general medicine, gastroenterology, orthopaedic and radiology domain are used. MT Sample Dataset is used to collect 1040 different transcripts. Using the proposed approach, an average ROUGE score of 0.77 for single-document summarization; however, for generic summary, an average ROUGE is 0.72. The proposed technique is validated for the previous corpus of BioMed articles, and results are better with state-of-the-art techniques.

show abstract

Supporting Online Video Learning with Concept Map-based Recommendation of Learning Path

Cited by 9 publications

References 15 publications

Critical reflections on three popular computational linguistic approaches to examine Twitter discourses

Critical reflections on three popular computational linguistic approaches to examine Twitter discourses

Personalized Learning Path Recommendation Based on Weak Concept Mining

Extractive summarization using concept‐space and keyword phrase

Contact Info

Product

Resources

About