“…This success has been shown with textual data in the course forum in Ref. 4. The second is their capability of examining spatial-temporal associations layer by layer in inputs.…”
Section: The Proposed Cnn Models With Additional Enhancementsmentioning
confidence: 94%
“…Compared to each other, MFE is less complex than MSFE although Ref. 4 has confirmed the more effectiveness of MSFE. In the context of our task, data shortage makes us hard to anticipate if MSFE is still more effective.…”
Section: New Loss Functions For Binary Cnn Modelsmentioning
confidence: 97%
“…They were also examined in Ref. 4 for effectiveness confirmation on temporal educational data with data imbalance at the course level. Nevertheless, it is questionable to pick a proper loss function for deep learning on temporal educational dataat the program level.…”
In educational data mining, student classification is an important and popular task by predicting final study status of each student. In the existing works, this task has been considered in many various contexts at both course and program levels with different learning approaches.However, its realworld characteristics such as temporal aspects, data imbalance, data overlapping, and data shortage with sparseness have not yet been fully investigated. Making the most of deep learning, our work is the first one addressing those challengesfor the program-level student classification task. In a simple but effective manner, convolutional neural networks (CNNs) are proposed to exploit their wellknown advantages on images for temporal educational data. As a result, the task is resolved by our enhanced CNN models with more effectiveness and practicability on real datasets. Our CNN models outperform other traditional models and their various variants on a consistent basis for program-level student classification.
“…This success has been shown with textual data in the course forum in Ref. 4. The second is their capability of examining spatial-temporal associations layer by layer in inputs.…”
Section: The Proposed Cnn Models With Additional Enhancementsmentioning
confidence: 94%
“…Compared to each other, MFE is less complex than MSFE although Ref. 4 has confirmed the more effectiveness of MSFE. In the context of our task, data shortage makes us hard to anticipate if MSFE is still more effective.…”
Section: New Loss Functions For Binary Cnn Modelsmentioning
confidence: 97%
“…They were also examined in Ref. 4 for effectiveness confirmation on temporal educational data with data imbalance at the course level. Nevertheless, it is questionable to pick a proper loss function for deep learning on temporal educational dataat the program level.…”
In educational data mining, student classification is an important and popular task by predicting final study status of each student. In the existing works, this task has been considered in many various contexts at both course and program levels with different learning approaches.However, its realworld characteristics such as temporal aspects, data imbalance, data overlapping, and data shortage with sparseness have not yet been fully investigated. Making the most of deep learning, our work is the first one addressing those challengesfor the program-level student classification task. In a simple but effective manner, convolutional neural networks (CNNs) are proposed to exploit their wellknown advantages on images for temporal educational data. As a result, the task is resolved by our enhanced CNN models with more effectiveness and practicability on real datasets. Our CNN models outperform other traditional models and their various variants on a consistent basis for program-level student classification.
“…However, Ref. 16 considered only predictions for the students who have posted messages in the forum, while this paper takes all the students with and without forum posts into account. Such a main difference leads the task in this paper to a more practical but more challenging context.…”
Nowadays, teaching and learning activities in a course are greatly supported by information technologies. Forums are among information technologies utilized in a course to encourage students to communicate with lecturers more outside a traditional class. Free-styled textual posts in those communications express the problems that the students are facing as well as the interest and activeness of the students with respect to each topic of a course. Exploiting such textual data in a course forum for course-level student prediction is considered in our work. Due to hierarchical structures in course forum texts, we propose a solution in this paper which combines a deep convolutional neural network (CNN) and a loss function to extract the features from textual data in such a manner that more correct recognitions of instances of the minority class which includes students with failure can be supported. In addition, other numeric data are examined and used for the task so that all the students with and without posts can be predicted in the task. Therefore, our work is the first one that defines and solves this prediction task with heterogeneous educational data at the course level as compared to the existing works. In the proposed solution, Random Forests are suggested as an effective ensemble model suitable for our heterogeneous data when many single prediction models which are random trees can be built for many various subspaces with different random features in a supervised learning process. Experimental results in an empirical evaluation on two real datasets show that a heterogeneous combination of textual and numeric data with a Random Forest model can enhance the effectiveness of our solution to the task. The best accuracy and [Formula: see text]-measure values can be obtained for early predictions of the students with either success or failure. Such better predictions can help both students and lecturers beware of students’ study and support them in time for ultimate success in a course.
“…Long short-term memory (LSTM) and the gated recurrent unit were developed to alleviate the limitation of vanishing gradient of the basic recurrent neural network. For example, Nguyen et al applied a deep CNN to course-level prediction based on forum posts for correct recognition of instances of the minority class which included learners with failing grades [39]. Ramón et al utilized a CNN to detect the positive or negative polarity of learners' opinions regarding the exercises they solved in an intelligent learning environment [6].…”
Section: Sentiment Classification Of Mooc Forum Postsmentioning
Sentiment classification of forum posts of massive open online courses is essential for educators to make interventions and for instructors to improve learning performance. Lacking monitoring on learners' sentiments may lead to high dropout rates of courses. Recently, deep learning has emerged as an outstanding machine learning technique for sentiment classification, which extracts complex features automatically with rich representation capabilities. However, deep neural networks always rely on a large amount of labeled data for supervised training. Constructing large-scale labeled training datasets for sentiment classification is very laborious and time consuming. To address this problem, this paper proposes a co-training, semi-supervised deep learning model for sentiment classification, leveraging limited labeled data and massive unlabeled data simultaneously to achieve performance comparable to those methods trained on massive labeled data. To satisfy the condition of two views of co-training, we encoded texts into vectors from views of word embedding and character-based embedding independently, considering words' external and internal information. To promote the classification performance with limited data, we propose a double-check strategy sample selection method to select samples with high confidence to augment the training set iteratively. In addition, we propose a mixed loss function both considering the labeled data with asymmetric and unlabeled data. Our proposed method achieved a 89.73% average accuracy and an 93.55% average F1-score, about 2.77% and 3.2% higher than baseline methods. Experimental results demonstrate the effectiveness of the proposed model trained on limited labeled data, which performs much better than those trained on massive labeled data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.