A Comprehensive Evaluation of Emotion Recognition Techniques: Model and Data Analysis
Bibliographic record
Abstract
This study evaluates three prominent techniques for emotion recognition: Convolutional Neural Networks (CNNs), the Emotions in Context (EMOTIC) dataset, and feature extraction methods like Principal Component Analysis (PCA) and Local Phase Quantization (LPQ). By analyzing these methods across datasets such as Fuyeor Language (FER) 2013 and EMOTIC, the research highlights CNNs' ability to classify emotions from Electroencephalogram (EEG) signals with high accuracy, enhanced by PCA's dimensionality reduction. The EMOTIC dataset's fine-grained emotional categories, combined with contextual data, improved emotion detection in real-world settings, particularly when facial expressions alone were insufficient. LPQ further enhanced texture analysis in challenging environments with variable lighting. While CNNs demonstrated strong performance, challenges like real-time processing and generalization across diverse datasets remain. Future work should focus on integrating audio and physiological data and incorporating temporal information to detect dynamic emotional changes. These developments will help only in creating a better and generalized emotion detection system for the respective areas like healthcare, virtual reality, and interaction with the virtual world.
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 | 0.008 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".