EmoBlend Fusion: Leveraging Handcrafted and Deep Features for Emotion Detection
Bibliographic record
Abstract
Correct detection of human emotions plays a vital role in human-machine communication and decision-making. Recent advancements in large language models (LLMs) have sparked research in opinion mining, emotion detection, and sentiment analysis. While features extracted from texts using pre-trained LLMs can capture patterns effectively, integrating domain-specific handcrafted features remains crucial for constructing predictive models using user-generated microblogs. This paper proposes EmoBlend Fusion, a hybrid emotion detection model incorporating handcrafted features and latent deep features using pre-trained embeddings extracted from tweets. While the handcrafted features are trained using an ensemble of random forest, XGBoost, and linear SVM classifiers, a new bidirectional convolutional neural network-based model is trained using the deep features. Model predictions are then fused through a weighted ensemble mechanism for classifying emotions into one of the six distinct classes: sadness, joy, love, anger, fear, and surprise. The experimental results demonstrate that the proposed model outperforms the state-of-the-art techniques, achieving the highest recall (0.94), precision (0.95), accuracy (0.94), and F1-score (0.94) on a benchmark Twitter emotion detection dataset.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".