Needle in a haystack: Identifying learner posts that require urgent response in MOOC discussion forums

Almatrafi, Omaima; Johri, Aditya; Rangwala, Huzefa

doi:10.1016/j.compedu.2017.11.002

Cited by 110 publications

(81 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past few years, researchers have made substantial progress in mining data from MOOCs, such as mining texts from discussion forums [7], mining video behaviors [8,9], performance prediction [10,13,21,23], plagiarism detection [11,12], and dropout detection [18,19]. These data mined from MOOCs have been widely used for predicting student achievement.…”

Section: Prediction In Moocsmentioning

confidence: 99%

“…The calculation process of the output results is shown in Equations (1)- (7). The new memory, C t , is generated from the output, h t−1 and x t , of the previous unit.…”

Section: Multi-layer Lstm Neural Networkmentioning

confidence: 99%

“…A multi-layer LSTM network generally consists of three layers: (1) An input layer, (2) a hidden layer, and 3 The calculation process of the output results is shown in Equations (1)- (7). The new memory, Ct, is generated from the output, ht−1 and xt, of the previous unit.…”

Section: Multi-layer Lstm Neural Networkmentioning

confidence: 99%

“…Researchers are committed to improving the effectiveness of learning in many ways. Previous work has tried to predict and improve student achievement in MOOCs by considering courses [5,6], forums [7], watching behaviors on video [8,9], quizzes [10], plagiarism [11,12], and so on.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predicting Student Achievement Based on Temporal Learning Behavior in MOOCs

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

With the development of data mining technology, educational data mining (EDM) has gained increasing amounts of attention. Research on massive open online courses (MOOCs) is an important area of EDM. Previous studies found that assignment-related behaviors in MOOCs (such as the completed number of assignments) can affect student achievement. However, these methods cannot fully reflect students’ learning processes and affect the accuracy of prediction. In the present paper, we consider the temporal learning behaviors of students to propose a student achievement prediction method for MOOCs. First, a multi-layer long short-term memory (LSTM) neural network is employed to reflect students’ learning processes. Second, a discriminative sequential pattern (DSP) mining-based pattern adapter is proposed to obtain the behavior patterns of students and enhance the significance of critical information. Third, a framework is constructed with an attention mechanism that includes data pre-processing, pattern adaptation, and the LSTM neural network to predict student achievement. In the experiments, we collect data from a C programming course from the year 2012 and extract assignment-related features. The experimental results reveal that this method achieves an accuracy rate of 91% and a recall of 94%.

show abstract

Section: Prediction In Moocsmentioning

confidence: 99%

“…The calculation process of the output results is shown in Equations (1)- (7). The new memory, C t , is generated from the output, h t−1 and x t , of the previous unit.…”

Section: Multi-layer Lstm Neural Networkmentioning

confidence: 99%

Section: Multi-layer Lstm Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Student Achievement Based on Temporal Learning Behavior in MOOCs

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…They came to the conclusion that the linguistic model for classification that distinguishes the posts related to the content from those unrelated to content can be generalised to other statistics courses, even though they considered that the model would be less efficient in other areas. Similarly,Almatrafi et al (2018) aimed to facilitate instructors' role in MOOCs. More specifically, this study sought to assist them in navigating students' posts in MOOC discussion forums in a more efficient and effective way.…”

mentioning

confidence: 99%

Research on MOOCs in Major Referred Journals

Babori

Zaid

Fassi

2019

IRRODL

View full text Add to dashboard Cite

Over the last decade, several studies have focused on massive open online courses (MOOCs). The synthesis presented here concentrates on these studies and aims to examine the place held by content in these studies, especially those produced between 2012 and 2018: sixty-five peer reviewed papers are identified through five major educational technology research journals. The analysis revealed that these research articles covered a wide diversity of content. Content was mainly defined in terms of objectives of MOOCs, prerequisites required for participation in the MOOC, types of learning scenarios, and, though rarely, through the strategies used to convey content. In addition, empirical studies adopted a variety of conceptual frameworks which focused mainly on learning strategies without relating to the content in question. Finally, content was seldom considered as a research object. These results can provide MOOC researchers and instructors with insights for the study and design of MOOCs by taking into account the specificity of their content.

show abstract

“Houston, we have a problem”: Revealing MOOC practitioners' experiences regarding feedback provision to learners facing difficulties

Topali

Ortega‐Arranz

Martínez‐Monés

et al. 2020

Comp Applic In Engineering

View full text Add to dashboard Cite

In spite of the high impact of Massive Open Online Courses (MOOCs), learners frequently disengage from the course contents and activities due to unexpected problems of different natures, such as content-related or technical issues. Feedback has been identified as an important aspect of the learning process directly connected with learners' engagement. However, the massive and impersonal nature of MOOCs hinders the provision of efficient and timely feedback to those learners facing problems. This paper examines how MOOC practitioners identify and support learners facing problems, what challenges they encounter, and what strategies they apply to overcome such challenges.Additionally, the current study aims to compare the learners' problems and practitioners' experiences between engineering-related and nonengineering related MOOCs. A qualitative phenomenological study has been conducted through semistructured interviews with 14 MOOC practitioners. The evidence gathered shows diverse learners' and practitioners' problems shared among engineering and nonengineering courses and a general concern on how to address individual learners' needs in time. A common practice of problem identification regards checking the self-reported issues in communication forums. Identification strategies with the use of learning analytics are limited due to platform restrictions or lack of practitioners' skills in interpreting the provided information. The synthesis of MOOC practitioners from both engineering and nonengineering disciplines may provide insights that are either globally applicable to all disciplines or specific to engineering. The results could be shaped into conceptual and technological solutions to help MOOC stakeholders (e.g., researchers, practitioners) identify potential learners facing difficulties and support them during the course process.

show abstract

Needle in a haystack: Identifying learner posts that require urgent response in MOOC discussion forums

Cited by 110 publications

References 9 publications

Predicting Student Achievement Based on Temporal Learning Behavior in MOOCs

Predicting Student Achievement Based on Temporal Learning Behavior in MOOCs

Research on MOOCs in Major Referred Journals

“Houston, we have a problem”: Revealing MOOC practitioners' experiences regarding feedback provision to learners facing difficulties

Contact Info

Product

Resources

About