Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198464,
        author = {Jignasha Makwana and Prof. Rupal J. Shilu},
        title = {Emotion Recognition from EEG Signals: A Review of Machine Learning and Deep Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {9466-9472},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198464},
        abstract = {Within affective computing and brain-computer interfaces (BCI), electroencephalogram (EEG) signal-based emotion identification has become a potential area of study. The limits of subjective self-reports or external modalities are overcome by EEG, which offers direct access to internal brain correlates of emotional states. Using data from 12 current research published between 2021 and 2025, this study thoroughly investigates machine learning (ML) and deep learning (DL) techniques for EEG-based emotion categorization. With the use of advanced feature extraction methods (such as spectrograms, differential entropy, and wavelet transformations) and strategies like data augmentation, attention mechanisms, and optimization algorithms, machine learning (ML) may achieve 99.9% accuracy. Although there are still issues like subject variability, noise, and a lack of labeled data, hybrid and multimodal approaches have a lot of promise. Recommendations for further study toward more reliable, deployable systems in the actual world are included in the review's conclusion.},
        keywords = {EEG, Emotion Recognition, Machine Learning, Deep Learning, CNN, SVM, Random Forest, DEAP Dataset},
        month = {April},
        }