Skip to main content
ABCT 2024 58th Annual Convention Main banner
Psychology Tools Ad
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Recorded Session
Recorded Session
Ticketed Session
Ticketed Session
Back
ViewAttendees 6

Symposia

Assessment

New Research Findings in Digital Phenotyping of Psychological Phenomena

5 - (SYM 111) Harnessing Smartphone Data for Personalized Prediction of States of Heightened Negative Affect

Sunday, November 17, 2024
8:30 AM – 10:00 AM EST
Location: Grand Ballroom A, Level 5, Downtown Marriott
Abstract Body

Objective: Disturbance in negative affect (e.g., heightened sadness, anxiety, or anger) is a core feature of affective disorders. Over 90% of American adults own a smartphone, equipped with an array of sensors which can continuously and unobtrusively measure behaviors (e.g., activity levels, location, and phone usage patterns) which may predict increases in negative affect in real-time in individuals' daily lives.



Method: 42 adults (74% with a primary affective disorder) completed daily emotion surveys over 200 days, on average. At the same time, semi-continuous collection of smartphone accelerometer, GPS location, and screen usage data, along with movement tracking from an actigraphy watch, was conducted for the duration of the study. A range of statistical approaches, including a novel personalized ensemble machine learning algorithm, were compared in their ability to predict states of heightened negative affect.



Results: A personalized ensemble machine learning algorithm outperformed other statistical approaches, achieving an area under the curve (AUC) of 0.72-0.79 in predicting different negative emotions. Smartphone location (GPS) variables were the most predictive features overall. Critically, there was substantial heterogeneity between individuals in the association between different smartphone features and negative emotional states, which highlights the need for a personalized modeling approach.



Conclusions: Findings support the use of smartphones coupled with machine learning to detect states of heightened negative emotions. The ability to predict these states in real-time could inform the development and timely delivery of emotionally beneficial smartphone-delivered interventions which could be automatically triggered by a predictive algorithm.