Research on MOOC Reviews Oriented Sentiment Analysis by Awareness of Emotional Distinctions
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
It is essential for MOOCs to understand the learner’s emotions. This study aims to develop a novel sentiment analysis model to automatically classify the emotions of MOOC learners, which is beneficial to educators and instructors in improving the quality of courses and platform design in MOOCs. Firstly, a robust and interpretable model was proposed, named BB-OAM, which incorporated BERT, attention method, and BiLSTM to extract features of forum reviews as accurately as possible. To capture and differentiate among various affective tendencies more effectively in sentiment analysis, we have taken a breakthrough by introducing an orthogonal attention mechanism to enhance the model’s performance for emotion-ambiguous sentences. Compared with models in previous studies including SVM, Tree-CRF, BiRNN, LSTM, and BiLSTM, our method improved the accuracy value of sentiment analysis by 24%, 24%, 19%, 17%, and 9% respectively. Ablation experiments were conducted to systematically evaluate the impact of the orthogonal attention mechanism on sentiment analysis. Through visualization analysis, the model showed higher sensitivity in capturing sentiment-related contents, which further validated the reliability and effectiveness of the proposed method in sentiment classification tasks of MOOC reviews. In essence, this study has great methodological and theoretical insights to help educators and instructors gain a deeper understanding of the actual needs of learners, so as to optimize the efficiency of utilizing MOOC platforms and courses, and to promote effective interactions and collaboration between learners and educators.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it