A Novel Approach Using D2RM for Enhancing the User Experience in Mood Detection and Recommendation Activity

The fastest developing culture of smartphones has revolutionized user experiences, particularly in developing medical technology. AI tools, along with relevant data, provide personalized solutions to improve things to do by considering the user's mood. Regular recommendation systems frequently fail to adjust to unpredictable mood changes, rendering them ineffective in dealing with users' mental health. Difficulties such as inconsistent mood identification and processing limits exist, particularly in noisy situations. To address these constraints, a inclusive strategy, the Dynamic Mood Recognition and Recommendation Model (D2RM), is developed that uses user information to improve personalization. The constructed model obtained 94.3 % accuracy, MAE of 0.12, and 42 % of user engagement. This approach improves mobile user interfaces by matching recommendations to immediate mood swings, establishing a standard for savvy and flexible AI-driven medical services.