Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums
The Massive Open Online Courses (MOOCs) platform offers communication channels for students to share concerns about the educational process. Due to the large number of students compared to the instructors’, it is challenging to identify urgent forum posts that require attention and prompt response f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-04-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S209044792300494X |
| _version_ | 1797238038043033600 |
|---|---|
| author | Mohamed A. El-Rashidy Nabila A. Khodeir Ahmed Farouk Heba K. Aslan Nawal A. El-Fishawy |
| author_facet | Mohamed A. El-Rashidy Nabila A. Khodeir Ahmed Farouk Heba K. Aslan Nawal A. El-Fishawy |
| author_sort | Mohamed A. El-Rashidy |
| collection | DOAJ |
| description | The Massive Open Online Courses (MOOCs) platform offers communication channels for students to share concerns about the educational process. Due to the large number of students compared to the instructors’, it is challenging to identify urgent forum posts that require attention and prompt response from the instructor. This paper presents an innovative automated classification model called the “Attention Based on Contextual Local and Global Features (AT-CX-LGF)” classifier to identify MOOCs’ urgent posts. It can aid instructors in managing many posts and prioritizing their responses, allowing them to respond more quickly to student questions and reduce dropout rates while increasing completion rates. The suggested model obtains word embedding to represent the context information using BERT (Bidirectional Encoder Representation from Transformer). It depends on several phases. First, it extracts local and semantic (or global) contextual features using multi-layer CNN and Bi-LSTM. Then, two attention layers parallelly identify the most significant local and global features. After that, the outputs of the attention layers are concatenated and normalized. Finally, fully connected, and sigmoid layers are used for the classification process. On three groups (A, B, C) gathered from the Stanford MOOC Posts dataset, the AT-CX-LGF classifier obtained urgent posts recall of 87%, 87.1%, and 90.6% with 5.5%, 2.4%, and 7.5% improvements over the most recent algorithms, respectively. Furthermore, the model outperformed the state-of-the-art method in the weighted F1-score with handling the concept drift of the dataset. |
| first_indexed | 2024-04-24T17:29:17Z |
| format | Article |
| id | doaj.art-560e6b14204b4aa3937ab5e2e7d7b9d9 |
| institution | Directory Open Access Journal |
| issn | 2090-4479 |
| language | English |
| last_indexed | 2024-04-24T17:29:17Z |
| publishDate | 2024-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj.art-560e6b14204b4aa3937ab5e2e7d7b9d92024-03-28T06:37:31ZengElsevierAin Shams Engineering Journal2090-44792024-04-01154102605Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forumsMohamed A. El-Rashidy0Nabila A. Khodeir1Ahmed Farouk2Heba K. Aslan3Nawal A. El-Fishawy4Department of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University, Egypt; Department of Computer, Arab East Colleges, Saudi ArabiaDeparment of Informatics, Electronics Research Institute, EgyptDeparment of Informatics, Electronics Research Institute, Egypt; Corresponding author.Centre of Informatics Science, Faculty of Information Technology and Computer Science, Nile University, EgyptDepartment of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University, EgyptThe Massive Open Online Courses (MOOCs) platform offers communication channels for students to share concerns about the educational process. Due to the large number of students compared to the instructors’, it is challenging to identify urgent forum posts that require attention and prompt response from the instructor. This paper presents an innovative automated classification model called the “Attention Based on Contextual Local and Global Features (AT-CX-LGF)” classifier to identify MOOCs’ urgent posts. It can aid instructors in managing many posts and prioritizing their responses, allowing them to respond more quickly to student questions and reduce dropout rates while increasing completion rates. The suggested model obtains word embedding to represent the context information using BERT (Bidirectional Encoder Representation from Transformer). It depends on several phases. First, it extracts local and semantic (or global) contextual features using multi-layer CNN and Bi-LSTM. Then, two attention layers parallelly identify the most significant local and global features. After that, the outputs of the attention layers are concatenated and normalized. Finally, fully connected, and sigmoid layers are used for the classification process. On three groups (A, B, C) gathered from the Stanford MOOC Posts dataset, the AT-CX-LGF classifier obtained urgent posts recall of 87%, 87.1%, and 90.6% with 5.5%, 2.4%, and 7.5% improvements over the most recent algorithms, respectively. Furthermore, the model outperformed the state-of-the-art method in the weighted F1-score with handling the concept drift of the dataset.http://www.sciencedirect.com/science/article/pii/S209044792300494XMulti-head self-attentionMOOCsNatural language processingDeep learningBERT |
| spellingShingle | Mohamed A. El-Rashidy Nabila A. Khodeir Ahmed Farouk Heba K. Aslan Nawal A. El-Fishawy Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums Ain Shams Engineering Journal Multi-head self-attention MOOCs Natural language processing Deep learning BERT |
| title | Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums |
| title_full | Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums |
| title_fullStr | Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums |
| title_full_unstemmed | Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums |
| title_short | Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums |
| title_sort | attention based contextual local and global features for urgent posts classification in moocs discussion forums |
| topic | Multi-head self-attention MOOCs Natural language processing Deep learning BERT |
| url | http://www.sciencedirect.com/science/article/pii/S209044792300494X |
| work_keys_str_mv | AT mohamedaelrashidy attentionbasedcontextuallocalandglobalfeaturesforurgentpostsclassificationinmoocsdiscussionforums AT nabilaakhodeir attentionbasedcontextuallocalandglobalfeaturesforurgentpostsclassificationinmoocsdiscussionforums AT ahmedfarouk attentionbasedcontextuallocalandglobalfeaturesforurgentpostsclassificationinmoocsdiscussionforums AT hebakaslan attentionbasedcontextuallocalandglobalfeaturesforurgentpostsclassificationinmoocsdiscussionforums AT nawalaelfishawy attentionbasedcontextuallocalandglobalfeaturesforurgentpostsclassificationinmoocsdiscussionforums |