Algorithmic Arias

Music has a profound impact on our emotional well-being, and music therapy has proven effective in various healthcare settings. However, traditional methods of music therapy lack real-time personalization. This research explores the potential of personalized music therapy using Affective Algorithmic Composition (AAC) and facial recognition technology. The focus is on harnessing the power of AAC to generate music tailored to an individual's emotional state in real-time. Existing research confirms the strong connection between music and the brain, demonstrating the effectiveness of music therapy in various healthcare settings, and facial recognition technology provides a cost-effective and versatile tool to measure these emotions. While the field of AAC is experiencing significant growth, user preferences and the factors influencing them are crucial for developing successful real-time personalized music experiences. To gain insights into these aspects, a survey (n=160) was conducted to collect data on demographics, music listening habits, and influences on musical preferences across a range of ages. While the sample had a significant portion of teenagers (14-15 years old), responses from all age groups contributed to a comprehensive understanding of music preferences and their potential connection to emotions across the lifespan. Future studies will focus on refining emotion detection algorithms, optimizing AAC for real-time music generation, and conducting clinical trials to evaluate the effectiveness of this approach.