A Method to Classify Emotions Based on BERT
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
Nowadays, as science and technology continue to advance, addressing people's emotional issues is of particular significance, and how to accurately and efficiently recognize emotions has become increasingly prominent. We explores sentiment recognition and classification methods, including rule-based approaches, traditional machine learning models, deep learning models, and multi-modal sentiment analysis. Through comparative analysis, we will evaluate the effectiveness of these methods in handling social media texts. Additionally, we has developed a BERT-based two-stage model that first determines sentiment polarity (positive or negative) and then performs detailed classification of negative emotions. This two-stage model significantly improves accuracy and detail recognition compared to traditional one-stage models and other baseline methods. The results show that our approach not only enhances sentiment analysis accuracy but also provides deeper insights into the emotional subtleties of social media texts. This advancement holds significant practical implications for real-time sentiment monitoring and more effective crisis management strategies.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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