Deep Learning for Discussion-Based Cross-Domain Performance Prediction of MOOC Learners Grouped by Language on FutureLearn

Duru, İsmail; Sunar, Ayşe Saliha; White, Su; Di̇ri̇, Banu

doi:10.1007/s13369-020-05117-x

Cited by 11 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, more research is needed to replicate our procedure and investigate if more sophisticated features based on natural language other than unigrams (e.g., n-grams, sentence embeddings, or sentiment analysis) could shed more light on linguistic associations of think-aloud data with in-tutor correctness. Related work on learning in MOOCs showed some merit in predicting learner performance from such linguistic features extracted from discussion posts [17]. Another area of future work is to investigate if the use (or lack) of domain-specific vocabulary can guide adaptivity in tutoring software.…”

Section: Discussionmentioning

confidence: 99%

Using Think-Aloud Data to Understand Relations between Self-Regulation Cycle Characteristics and Student Performance in Intelligent Tutoring Systems

Borchers,

Zhang,

Baker

et al. 2024

Proceedings of the 14th Learning Analytics and Knowledge Conference

View full text Add to dashboard Cite

Numerous studies demonstrate the importance of self-regulation during learning by problem-solving. Recent work in learning analytics has largely examined students' use of SRL concerning overall learning gains. Limited research has related SRL to in-the-moment performance differences among learners. The present study investigates SRL behaviors in relationship to learners' moment-by-moment performance while working with intelligent tutoring systems for stoichiometry chemistry. We demonstrate the feasibility of labeling SRL behaviors based on AI-generated think-aloud transcripts, identifying the presence or absence of four SRL categories (processing information, planning, enacting, and realizing errors) in each utterance. Using the SRL codes, we conducted regression analyses to examine how the use of SRL in terms of presence, frequency, cyclical characteristics, and recency relate to student performance on subsequent steps in multi-step problems. A model considering students' SRL cycle characteristics outperformed a model only using in-the-moment SRL assessment. In line with theoretical predictions, students' actions during earlier, process-heavy stages of SRL cycles exhibited lower moment-by-moment correctness during problem-solving than later SRL cycle stages. We discuss system re-design opportunities to add SRL support during stages of processing and paths forward for using machine learning to speed research depending on the assessment of SRL based on transcription of think-aloud data.

show abstract

Section: Discussionmentioning

confidence: 99%

Using Think-Aloud Data to Understand Relations between Self-Regulation Cycle Characteristics and Student Performance in Intelligent Tutoring Systems

Borchers,

Zhang,

Baker

et al. 2024

Proceedings of the 14th Learning Analytics and Knowledge Conference

View full text Add to dashboard Cite

show abstract

“…Another learner commented that “The course will be more vivid, humorous, and interesting, maintaining the interaction between teachers and students, and thereby encouraging students to grasp this knowledge more solidly through more practical cases”. Some medical courses involving practice ¾ which virtual online teaching cannot provide ¾ should be conducted in a real environment[ 31 , 36 ].…”

Section: Discussionmentioning

confidence: 99%

Behavior analysis and formative assessments in online oral medicine education during the COVID-19 pandemic

Ye¹,

Zhao²,

Teng³

et al. 2023

World J Clin Cases

View full text Add to dashboard Cite

The modern medical education system has gradually evolved starting from 1910 incorporating the suggestions by Abraham Flexner, his public disclosure of the poor conditions at many medical schools provided a means to galvanize all the constituencies needed for reform to occur. He could say what other reformers could not, due to their links to the medical education community. But now we are again going back to a pre-Flexnerian state due to multiple reasons such as gradually diminishing importance of basic science subjects for the students, the decline in the number and quality of investigator initiated research among clinical researchers, lesser emphasis to bedside training by means of detailed clinical examination and making appropriate observation of signs to reach to a diagnosis rather than over reliance on the laboratory tests and radiological modalities for the diagnosis, poor exposure to basic clinical skills starting from college throughout residency and the trend of disrespect and absenteeism from both theoretical and clinical/practical classes. The attitude of students is just to complete their required attendance so that they are not barred from appearing in examinations. This de-Flexnerization trend and regression to pre-Flexnerian era standards, ideologies, structures, processes, and attitudes, are bound to beget pre-Flexnerian outcomes, for you get what you designed for.

show abstract

“…2) Deep learning models: Even though Deep Learning is not a new method, its use has recently become widespread due to emerging technologies in computer processing capabilities and a large amount of data available, which also leads to its applications in educational context [45]. We also observe in the literature analysis, nine of the papers (32%) exploit deep learning models to improve their already developed models or compare deep learning models with baseline machine learning models in predicting sentiment and/or category.…”

Section: B According To Methods and Modelsmentioning

confidence: 99%

Natural Language Processing of Student's Feedback to Instructors: A Systematic Review

Sunar,

Khalid

2024

IEEE Trans. Learning Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

Deep Learning for Discussion-Based Cross-Domain Performance Prediction of MOOC Learners Grouped by Language on FutureLearn

Cited by 11 publications

References 38 publications

Using Think-Aloud Data to Understand Relations between Self-Regulation Cycle Characteristics and Student Performance in Intelligent Tutoring Systems

Using Think-Aloud Data to Understand Relations between Self-Regulation Cycle Characteristics and Student Performance in Intelligent Tutoring Systems

Behavior analysis and formative assessments in online oral medicine education during the COVID-19 pandemic

Natural Language Processing of Student's Feedback to Instructors: A Systematic Review

Contact Info

Product

Resources

About