Typical Phone Use Habits: Intense Use Does Not Predict Negative Well-Being

Kleomenis Katevas, Ioannis Arapakis, Martin Pielot

Abstract

Not all smartphone owners use their device in the same way. In this work, we uncover broad, latent patterns of mobile phone use behavior. We conducted a study where, via a dedicated logging app, we collected daily mobile phone activity data from a sample of 340 participants for a period of four weeks. Through an unsupervised learning approach and a methodologically rigorous analysis, we reveal five generic phone use profiles which describe at least 10% of the participants each: limited use, business use, power use, and personality- & externally induced problematic use. We provide evidence that intense mobile phone use alone does not predict negative well-being. Instead, our approach automatically revealed two groups with tendencies for lower well-being, which are characterized by nightly phone use sessions.

Introduction

The prevailing narrative surrounding smartphone use often equates high screen time with "addiction" or poor mental health. However, much of the existing research relies on self-reported questionnaires, which are notoriously prone to memory bias. Furthermore, many studies treat all "heavy users" as a single, homogeneous group, overlooking the functional differences in how phones are used. This paper seeks to uncover the latent patterns of mobile behavior—the "typical habits"—and identify which specific behaviors actually correlate with negative well-being.

Methodology

The researchers employed a rigorous unsupervised learning pipeline on a dataset of 340 Android users in Spain (ages 18–66) over a four-week period. A custom logging app tracked 26 features, including screen unlocks, app categories (Social, Messaging, Email, Games), call frequency, battery drain, and ringer mode. The team evaluated 135 clustering configurations using rank aggregation across 13 internal validity metrics to identify the most robust model. Well-being was assessed using the Experience Sampling Method (ESM), with participants reporting their mood 10–15 times daily, alongside standardized psychometric tests like the PHQ-8 for depression and the Big Five personality test.

Results: Five Distinct User Profiles

The analysis identified five distinct user profiles based on their behavioral data:

  1. Limited Use (29%): Low usage across the board; the baseline group.
  2. Business Use (13%): Defined by a high volume of voice calls and minimal nightly sessions.
  3. Power Use (20%): High intensity and variety of app use; generally positive well-being.
  4. Personality-Induced Problematic Use (18%): High nightly usage and silent ringer mode; correlated with higher depression (PHQ-8) and neuroticism.
  5. Externally-Induced Problematic Use (20%): High nightly messaging and vibrate mode; linked to high stress during work hours with mood recovery on weekends.
Figure 2: Behavioral metrics across clusters, highlighting high call durations in C2 and increased night session durations in C4 and C5.

Discussion: Intensity vs. Timing

A key finding is the "Power User Paradox": while Cluster 3 users exhibited the highest overall usage and data consumption, they showed no significant negative well-being. They were actually more "awake" on weekends and less bored than other groups. In contrast, Clusters 4 and 5 exhibited lower well-being despite potentially lower total screen time than Power Users. The strongest predictor of stress and depression was not total hours used, but the timing of use—specifically sessions occurring between 0:00 and 5:59 AM.

Additionally, ringer mode emerged as a significant behavioral marker. Users in problematic clusters (C4 and C5) almost exclusively used silent or vibrate modes, whereas Limited and Business users preferred normal ringer settings. This suggests that those with lower well-being may be more sensitive to notification-induced stress or use silent modes as a coping mechanism for anxiety.

Figure 3: Technical and environmental markers, showing high battery drain for Power Users (C3) and distinct ringer mode preferences for problematic use clusters (C4 and C5).

Conclusion and Future Work

This research demonstrates that "extensive use" is not synonymous with "problematic use." By distinguishing between functional intensity and disruptive habits like nighttime scrolling, we can better understand the impact of technology on mental health. Future work should investigate the causal links between nighttime use and depression, as well as the psychological motivations behind ringer mode choices.

Limitations

The study was limited to Android users in Spain. Since mobile habits and cultural norms regarding late-night socializing can vary, future research should include iOS users and more diverse geographic demographics to validate these findings.

Summary updated

Abstract

Not all smartphone owners use their device in the same way. In this work, we uncover broad, latent patterns of mobile phone use behavior. We conducted a study where, via a dedicated logging app, we collected daily mobile phone activity data from a sample of 340 participants for a period of four weeks. Through an unsupervised learning approach and a methodologically rigorous analysis, we reveal five generic phone use profiles which describe at least 10% of the participants each: limited use, business use, power use, and personality- & externally induced problematic use. We provide evidence that intense mobile phone use alone does not predict negative well-being. Instead, our approach automatically revealed two groups with tendencies for lower well-being, which are characterized by nightly phone use sessions.
BibTeX
@inproceedings{katevas2018typical,
  author = {Kleomenis Katevas and Ioannis Arapakis and Martin Pielot},
  title = {{Typical Phone Use Habits: Intense Use Does Not Predict Negative Well-Being}},
  booktitle = {MobileHCI},
  year = {2018},
  url = {https://openreview.net/forum?id=bCnYhaoE2Lrx},
}
Figure