Business Success through Understanding Human Emotions: Case Study of Classifying Emotions using the Brain Waives EEG Data
Bibliographic record
Abstract
Emotion analytics applied in a business setting provide solutions to understand customer emotions or employee performance and carry out real-time AI analysis of the data.This is a smarter, much more unbiased alternative to such business tools as email surveys, mystery shoppers or "rate the service" buttonspractices that tend to be subjective and inconsistent and often fail to produce accurate and meaningful data.Many kinds of research are conducted to detect the emotion of a person by using different formats of data like speech, text, gesture and facial expressions.The problem with this data is that it will vary depending on the origin, culture, and nation.Because of this, it is difficult to detect human emotions more accurately.To solve this, our research makes use of electroencephalogram (EEG) signals that are directly collected from the brain.These signals not only ignore the external factors but also helps to detect real emotions arising from the brain.To conduct this research, a DEAP Dataset for emotion analysis using physiological signals is used.Firstly, the raw signal data is processed by removing the noise and converting the time series signal to statistical data.This statistical data is used to perform binary classification of four emotions valence, arousal, dominance, and liking.Various classifying techniques are examined to find the model that provides the best classification accuracy on this data.The experimental results show that Logistic Regression and Support Vector Machine are the best techniques for binary emotion classification with an accuracy of 69.25% and 70.35% respectively.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| 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".