Before You Scroll Again: Predicting Regretful Social Media Sessions from In-the-Wild Contextual and Wearable Sensing
2026-06-08 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors studied when people feel regret after using social media by tracking real phone use with a cheap smartwatch and surveys over a week. They found that regret is more linked to using social media longer than planned, not just how long the session was. Regret also increases when social media use replaces something important, especially at night or after doing productive tasks. They showed that some signals before using social media can predict regret, with general patterns across people and personal differences detected through body signals. Their work suggests ways to design better tools to help people avoid regret beyond just setting time limits.
social media regretexperience samplingsmartwatch dataintentions vs. behaviorcontextual featuresphysiological signalsjust-in-time interventionstime blindnessself-monitoringbehavior prediction
Authors
Sally Ahmed, Jan Enkmann, Kye Shimizu, Ivy Yip, Vincent Beermann, Ayse Alomar, Falk Uebernickel, Pattie Maes
Abstract
Users often feel regret after using social media, making regret a more ecologically valid target than screen time for understanding when phone use becomes problematic. Existing self-monitoring tools cannot anticipate regret before it occurs, and prior physiological work on social media use has been confined to the lab with research-grade sensors and curated content, leaving the question of in-the-wild prediction open. We deployed a 7-day in-the-wild experience sampling study with 21 participants, combining passive smartphone logging, a low-cost consumer smartwatch (Bangle.js 2, \$80), session-level surveys (1,445 sessions), and exit interviews to investigate when and why social media sessions become regretful, and whether regret can be anticipated before a session begins. Three findings stand out: (i) the gap between intended and actual use predicts regret far more strongly than session duration, with duration's apparent effect collapsing once intention is modeled; (ii) regret is amplified when sessions displace a valued alternative, particularly at night and following productivity-app use; and (iii) pre-session contextual features generalize across participants while physiological signals add person-specific lift, pointing toward a two-layer architecture for just-in-time adaptive interventions. Interview themes of scrolling-as-avoidance and time blindness contextualize these patterns and surface design opportunities beyond timer-based interventions.