Published Paper Details:

Maladaptive daydreaming (MD) is a psychological phenomenon characterized by excessive, immersive, and often compulsive daydreaming that significantly interferes with an individual's daily functioning, productivity, emotional regulation, and social interactions. Individuals suffering from MD may spend hours engaged in vivid fantasy worlds, which can lead to difficulties in academic, occupational, and interpersonal domains. Traditional therapeutic interventions, such as cognitive behavioral therapy (CBT) and mindfulness-based strategies, often require substantial human involvement and lack scalability, real-time monitoring, and personalized adaptation to individual user behavior. This paper introduces Daydream Detox, an innovative AI-driven therapeutic platform designed to detect, predict, and manage maladaptive daydreaming using advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Natural Language Processing (NLP). The system architecture integrates a Flutter-based mobile application for user interaction, a MERN (MongoDB, Express.js, React.js, Node.js) web dashboard for administrative and analytical oversight, a Python-based AI analytics module for emotion and behavior analysis, and a MongoDB database for secure data storage. Daydream Detox collects multidimensional user data, including activity patterns, text-based journals, mood logs, and user interaction metrics. This data is processed using NLP and ML algorithms to detect early signs of maladaptive daydreaming and generate predictive models of user behavior. The platform delivers personalized therapy plans, focus-enhancing routines, and context-aware recommendations tailored to individual needs. Furthermore, a real-time AI chatbot provides interactive interventions, motivational support, and reminders, thereby enhancing user engagement and adherence to therapy routines. Experimental evaluation involving multiple participants demonstrates that Daydream Detox significantly improves focus, reduces the frequency and duration of maladaptive daydreaming episodes, enhances emotional self-awareness, and promotes consistent adherence to personalized routines. The platform's AI-driven approach highlights the potential of digital therapeutics in providing scalable, adaptive, and real-time mental health support. This study emphasizes the importance of integrating AI, ML, and DL into digital wellbeing platforms and showcases how such technologies can address modern cognitive and emotional challenges effectively. Future work aims to expand the system with multimodal data inputs, such as speech and physiological signals, to further enhance predictive accuracy and therapeutic effectiveness.