Feeling the Facts: Real-time Wearable Fact-checkers Can Use Nudges to Reduce User Belief in False Information

Abstract

Misinformation can spread rapidly in everyday conversation, where pausing to verify is not always possible. We envision a wearable system that bridges the timing gap between hearing a claim and forming a judgment. It uses ambient listening to detect verifiable claims, performs rapid web verification, and provides a subtle haptic nudge with a glanceable overview. A controlled study (N=34) simulated this approach and tested against a no-support baseline. Results show that instant, body-integrated feedback significantly improved real-time truth discernment and increased verification activity compared to unsupported fact-checking. However, it also introduced over-reliance when the system made errors, i.e. failed to flag false claims or flagged true claims as false. We contribute empirical evidence of improved discernment alongside insights into trust, effort, and user-system tensions in verification wearables.

Figures (14)

• Figure 1: Overview: According to the dual-process theory, traditional pathway of information uptake (top) consists of triggers (T) such as curiosity leading to effortless engagement with new content (action (A)) and perceived knowledge gain (reward (R)), reinforcing fast, intuitive System 1 processing. Fact-Nudger (bottom) introduces subtle haptic nudges as alternative triggers, disrupting this loop and encouraging reflection and verification activities that engage slower, deliberate System 2 reasoning.
• Figure 2: Prototype Interaction Flow, that starts with the smartwatch listening for signals, the video sends signals to the watch when certain claims occur, and finally the watch vibrates and displays an explanation.
• Figure 3: Overview of the experimental procedure.
• Figure 4: Results for H1: Reducing Belief in Misinformation: (a) belief ratings across all conditions, (b) change in belief (post study -- baseline; -ve belief change means reduction in belief after intervention), and (c) confidence ratings across conditions. Error bars represent 95% confidence interval. Wilcoxon signed-rank test *p<0.05, **p<0.001, ***p<0.0001.
• Figure 5: (a) Results for H2: Promoting Verification Behavior -- Mean intervention duration (minutes), (b) Results for H2: Promoting Verification Behavior -- Total verification activities per participant. Error bars represent 95% confidence interval. Wilcoxon signed-rank test, ***p < 0.0001, ns is not significant. (c) Impact of nudge accuracy on belief change in the wearable condition. The inaccurate nudges for true claims indicate false positives (FP) or extra nudges, and the inaccurate nudges for false claims indicate false negatives (FN) or the nudges that were removed. Error bars represent 95% confidence interval. Mann Whitney U test *p < 0.05, ***p < 0.0001.