Brain-Computer Interfaces for Emotion Modulation: A User-Centered Study on EEG-Based Mood Regulation

Emotional regulation is a crucial aspect of mental well-being, and recent advancements in Brain-Computer Interfaces (BCI) have enabled the use of electroencephalography (EEG) signals for real-time mood detection and modulation. With systems like this, it is important to understand user preferences and emotional experiences. In this research we aim to explore how users would interact with and perceive automated mood recognition. We use an interactive EEG-based Mood Regulation System that classifies a user's emotional state and provides personalized interventions to either amplify or alter their mood. Using an EEG headset, the system detects affective states such as happiness, sadness, and anxiety, drawing upon established classification techniques from prior studies (Koelstra et al., 2012; Wang et al., 2023). For mood classification we use machine learning models such as Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs), trained on well-established EEG datasets like DEAP and SEED (Torres et al., 2020). Research has demonstrated the effectiveness of EEG-based mood tracking, particularly in understanding valence-arousal dimensions (Bano et al., 2022). To evaluate the system, a user study will be conducted where participants wear an EEG headset that detects their mood and presents two options: maintaining or shifting their emotional state. Based on their choice, the system delivers tailored audio-visual stimuli, including music, binaural beats, and immersive visuals, known to influence neural activity and emotions. We will record the users emotional states using their EEG signal and also make use of surveys to provide additional self-assessment and feedback about their experience and preferences. This study contributes to affective computing, neurotechnology, and human-computer interaction (HCI) by demonstrating a novel, real-time approach to personalized emotion regulation. Integrating BCI with neurofeedback offers applications in mental health, stress management, and adaptive AI-driven well-being. However, challenges such as EEG signal noise, inter-individual variability, and ethical concerns around emotion manipulation must be addressed for future development. By advancing BCI-driven emotional intelligence, this research underscores the potential of next-generation mood regulation systems for non-invasive, user-centered emotional well-being.