Emotions are complex psychological states that play a vital role. They influence our thoughts, behaviors, and interactions with others. While humans are experts at recognizing and understanding emotions in others, developing machines that can do the same remains challenging. Electroencephalography (EEG) is a non-invasive brain imaging technique that measures the brain's electrical activity. EEG signals are correlated with different emotional states, making them a promising source of information for emotion detection. Machine learning and deep learning are powerful artificial intelligence techniques that have revolutionized many fields, including emotion detection. Machine learning algorithms can be trained on EEG data to learn patterns associated with different emotions. Deep learning models can learn more complex patterns and achieve higher accuracy in emotion detection tasks. This review paper provides a comprehensive overview of EEG-based emotion detection using machine learning and deep learning approaches. We discuss the different EEG signal processing and feature extraction techniques commonly used in EEG-based emotion detection. We also review the different machine learning and deep learning algorithms used for EEG-based emotion detection. We then present a state-of-the-art review of the recent advances in EEG-based emotion detection. We discuss the challenges and limitations of existing EEG-based emotion detection models. Finally, we discuss the future directions of EEG-based emotion detection research. We highlight the potential applications of EEG-based emotion detection models in various fields, such as healthcare, education, and human–computer interaction. This review paper will be valuable for researchers and practitioners interested in EEG-based emotion detection.