Fitting the Message to the Moment: Designing Calendar-Aware Stress Messaging with Large Language Models

2025-05-29

AI Summary

Existing stress-management tools lack contextual and temporal awareness of students’ daily routines, limiting their ability to deliver timely, personalized support. This paper introduces a novel digital calendar–large language model (LLM) co-driven intervention paradigm: for the first time, personal calendar events serve as both real-time triggers and contextual inputs for LLM-generated stress prompts; structured prompting and tone calibration jointly ensure temporal precision and situational sensitivity. A one-week empirical probe study demonstrates that prompts prioritized by schedule urgency and expressed in concise, conversational language significantly improve student acceptability and perceived supportive efficacy. This work establishes a scalable technical pathway for dynamic health interventions and offers a human–AI collaborative design exemplar grounded in real-world temporal and contextual constraints.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Existing stress-management tools fail to account for the timing and contextual specificity of students' daily lives, often providing static or misaligned support. Digital calendars contain rich, personal indicators of upcoming responsibilities, yet this data is rarely leveraged for adaptive wellbeing interventions. In this short paper, we explore how large language models (LLMs) might use digital calendar data to deliver timely and personalized stress support. We conducted a one-week study with eight university students using a functional technology probe that generated daily stress-management messages based on participants' calendar events. Through semi-structured interviews and thematic analysis, we found that participants valued interventions that prioritized stressful events and adopted a concise, but colloquial tone. These findings reveal key design implications for LLM-based stress-management tools, including the need for structured questioning and tone calibration to foster relevance and trust.

Problem

• Existing stress tools lack timing and contextual specificity
• Digital calendar data is underused for adaptive wellbeing support
• LLMs can generate timely, personalized stress messages from calendars

Innovation

• LLMs generate personalized stress messages
• Calendar data guides timely interventions
• Concise colloquial tone fosters trust