Cancer survivors face unique mental health challenges, yet nearly half report unmet psychosocial needs. Smartphone interventions could help, but a major obstacle is knowing if, when, and how to intervene because inferring affective states with low-burden methods is hard. We test whether ultra-brief mobile diaries can infer contextual information approximating survivors’ affect, desire to regulate affect, and potential availability for brief digital behavioral interventions. Analyzing 24,183 entries from 407 survivors, administrative and health-related situations align with higher negative affect, whereas leisure/social situations align with higher positive affect. We introduce a Context-Aware LLM (CALLM) framework, which curates context via similarity-aligned peer cases and short personal trajectories, achieving balanced accuracy of 72.96% (positive affect), 73.29% (negative affect), 73.72% (regulation desire), and 60.09% (intervention availability), outperforming baselines. Post-hoc analyses show LLM confidence tracks accuracy, longer entries aid inference, and brief calibration improves personalization. Findings inform future just-in-time adaptive interventions for this underrepresented population.
ACM CHI Conference on Human Factors in Computing Systems