No abstract

No abstract

No abstract

A large number of people suffer from anxiety in modern society. As an effective treatment with few side effects, music therapy has been used to reduce anxiety for decades in clinical practice. Yet therapists continue to perform music selection, a key step in music therapy, manually. Considering the growing need for music therapy services and social distancing amid public emergencies, an automatic method for music selection would be of great practical utility. This paper marks the first effort to identify music with therapeutic effects on anxiety reduction via a novel music scoring model. We formulate the calculation of a therapeutic score as a quadratic programming problem, which minimizes score variance among known therapeutic songs while maintaining their superiority over other songs. The proposed model can uncover common features that contribute to anxiety reduction by learning from small and unbalanced data. Using a music therapy experiment, we find that the proposed model outperforms existing techniques in predicting therapeutic songs. Feature analysis is also conducted, revealing that high‐frequency spectrums are important in therapeutic scoring.