Sultani, Mujtaba, Daneshpour, Negin. (1405). Mining Student Opinions from MOOC Discussions Using a Multi-Output BERT-Based Deep Learning Approach. فناوری آموزش, 14(1), 145-162. doi: 10.22061/jecei.2025.11499.810
Mujtaba Sultani; Negin Daneshpour. "Mining Student Opinions from MOOC Discussions Using a Multi-Output BERT-Based Deep Learning Approach". فناوری آموزش, 14, 1, 1405, 145-162. doi: 10.22061/jecei.2025.11499.810
Sultani, Mujtaba, Daneshpour, Negin. (1405). 'Mining Student Opinions from MOOC Discussions Using a Multi-Output BERT-Based Deep Learning Approach', فناوری آموزش, 14(1), pp. 145-162. doi: 10.22061/jecei.2025.11499.810
Sultani, Mujtaba, Daneshpour, Negin. Mining Student Opinions from MOOC Discussions Using a Multi-Output BERT-Based Deep Learning Approach. فناوری آموزش, 1405; 14(1): 145-162. doi: 10.22061/jecei.2025.11499.810
1Faculty of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran.
2Computer Engineering Department, Shahid Rajaee Teacher Training University, Tehran, Iran.
تاریخ دریافت: 10 اردیبهشت 1404،
تاریخ بازنگری: 16 مرداد 1404،
تاریخ پذیرش: 25 مرداد 1404
چکیده
Background and Objectives: Massive Open Online Courses (MOOCs) face unique challenges in extracting student feedback from large, asynchronous student discussion forums. While traditional survey methods are commonly used, they struggle with scalability and real-time analysis in the MOOC context. This study aims to address these limitations and focus on automated extraction and classification of student opinions and their urgency. The study bridges the gap between suggestion mining in commercial applications and educational domains. Methods: We presented a novel deep learning approach using a BERT-based hybrid Convolutional Neural Network (CNN) – Bidirectional Long Short-term Memory (BiLSTM) multi-output model, named CBiLSTM. The model was trained to classify student posts into opinions and further categorize them by urgency. Performance metrics such as F1-weighted scores, Precision-Recall curves, and Area Under the Curve (AUC) were used to evaluate the model's efficacy, particularly in handling imbalanced datasets. Results: The presented CBiLSTM model got F1-weighted score of 87.3% for opinion classification and 81.1% for urgency classification which represents an improvement of 1.3% and 1.8% over the best-performing baseline model. Precision-Recall curves and AUC metrics highlights the model's strength in balancing precision and recall. These findings demonstrate the model's capacity to accurately classify and prioritize student feedback in the educational domain. Conclusion: This study offers a robust framework to enhance decision-making processes in MOOCs through effective feedback analysis. The CBiLSTM model provides a scalable, data-driven solution that empowers instructors, course designers, and policymakers to make targeted improvements, and improves student engagement and course quality.
