Akademik Veri Yönetim Sistemi
4th Eurasian Conference on Human-Computer Interaction (HCI-E 2025), Baku, Azerbaycan, 5 - 06 Aralık 2025, ss.1-15, (Tam Metin Bildiri)
Emotions are a fundamental part of human life and an important factor influencing individuals' thoughts, behaviors, and decisions. In the context of human-computer interaction, emotion recognition is becoming increasingly important, particularly for enriching the user experience and enabling more natural interactions. As a key component of affective computing, this capability allows systems to sense and adapt to users’ emotional states. Recently, there has been an increase in emotion recognition studies conducted using EEG signals. However, the multidimensional and noise-sensitive nature of EEG signals makes manual feature extraction difficult, making deep learning (DL) based approaches advantageous. This study systematically analyzes DL approaches applied to the widely used EEG-based emotion recognition datasets DEAP and DREAMER. A total of 185 scientific publications were evaluated in terms of fundamental stages such as signal preprocessing, feature extraction, and DL architectures. The findings reveal that the CNN architecture (N=129) is the most frequently used approach, followed by the LSTM (N=45) and GRU (N=16). Artifact removal, filtering, and normalization techniques are frequently applied in preprocessing steps, while frequency-based methods (N=132) are predominantly preferred for feature extraction. In the reviewed studies, various approaches have been employed depending on whether raw or preprocessed EEG signals were used and on model requirements. The study contributes to the literature by synthesizing current DL practices in EEG-based emotion recognition and by identifying common methodological patterns that may inform future research in the field.