PersoNo: Personalised Notification Urgency Classifier in Mixed Reality

2025-08-27

AI Summary

Frequent notifications in mixed reality (MR) environments disrupt user immersion. Method: This paper proposes a personalized notification urgency classification framework tailored for MR. It introduces the first MR-specific notification dataset, revealing that activity context is as critical as notification content and sender identity; designs a multi-agent classification architecture integrating user behavior, real-time activity context, and LLM-extracted response patterns; and employs a joint self-labeling and interactive feedback training strategy. Contribution/Results: User studies demonstrate an accuracy of 81.5% and a significantly reduced false positive rate of 0.381—outperforming existing baseline models. The approach establishes a scalable, context-aware paradigm for intelligent notification management in MR, advancing adaptive human–computer interaction in immersive environments.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Multiagent Systems: Agent Communication

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Mixed Reality (MR) is increasingly integrated into daily life, providing enhanced capabilities across various domains. However, users face growing notification streams that disrupt their immersive experience. We present PersoNo, a personalised notification urgency classifier for MR that intelligently classifies notifications based on individual user preferences. Through a user study (N=18), we created the first MR notification dataset containing both self-labelled and interaction-based data across activities with varying cognitive demands. Our thematic analysis revealed that, unlike in mobiles, the activity context is equally important as the content and the sender in determining notification urgency in MR. Leveraging these insights, we developed PersoNo using large language models that analyse users replying behaviour patterns. Our multi-agent approach achieved 81.5% accuracy and significantly reduced false negative rates (0.381) compared to baseline models. PersoNo has the potential not only to reduce unnecessary interruptions but also to offer users understanding and control of the system, adhering to Human-Centered Artificial Intelligence design principles.

Problem

• Classifying notification urgency in Mixed Reality
• Reducing disruptive interruptions during immersive experiences
• Personalizing alerts based on user behavior patterns

Innovation

• Personalized urgency classifier using LLMs
• Multi-agent approach reducing false negatives
• Leverages user behavior and context analysis