pith. sign in

arxiv: 2606.08965 · v1 · pith:OEONP5RPnew · submitted 2026-06-08 · 💻 cs.HC

Before You Scroll Again: Predicting Regretful Social Media Sessions from In-the-Wild Contextual and Wearable Sensing

Sally Ahmed , Jan Enkmann , Kye Shimizu , Ivy Yip , Vincent Beermann , Ayse Alomar , Falk Uebernickel , Pattie Maes This is my paper

Pith reviewed 2026-06-27 15:14 UTC · model grok-4.3

classification 💻 cs.HC
keywords social media regretexperience samplingwearable sensingintention mismatchcontextual predictionjust-in-time interventionsin-the-wild study
0
0 comments X

The pith

The gap between intended and actual social media use predicts regret far more strongly than session duration.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper deploys a week-long in-the-wild study with smartphone logging, consumer smartwatches, and experience sampling to examine regret after social media sessions. It establishes that the mismatch between what users plan and what they actually do is the dominant predictor of regret, while raw session length loses its apparent effect once intention is included in the model. Regret rises further when sessions displace valued alternatives, especially at night or after productivity-app use. Pre-session phone context generalizes across people, and wearable signals add individual accuracy, supporting layered prediction for timely interventions. Interview data on avoidance scrolling and time blindness supplies design implications beyond simple timers.

Core claim

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. Regret is amplified when sessions displace a valued alternative, particularly at night and following productivity-app use. 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.

What carries the argument

The intention-actual use gap measured through pre- and post-session surveys, combined with phone context logs and low-cost wearable signals to forecast regret before the session ends.

If this is right

  • Interventions should target closing the intention-use gap rather than imposing uniform time limits.
  • Higher-risk sessions occur at night and after productivity-app use when they displace other activities.
  • Contextual phone features can serve as a general first layer while wearable data supplies personalized lift.
  • Designs need to address scrolling-as-avoidance and time blindness instead of relying only on timers.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Apps could surface a quick intention prompt before social media opens to reduce later regret.
  • The same intention-gap logic might apply to other compulsive phone behaviors such as short-form video or gaming.
  • Longer deployments could test whether repeated intention alignment lowers cumulative regret and improves daily well-being.

Load-bearing premise

Participants' self-reported intentions and post-session regret ratings in the experience-sampling surveys accurately capture their true experiences and are not heavily biased by recall or social-desirability effects.

What would settle it

A study that directly logs or manipulates actual behavior against reported intentions and measures regret through non-self-report indicators would falsify the claim if the intention gap loses predictive power.

Figures

Figures reproduced from arXiv: 2606.08965 by Ayse Alomar, Falk Uebernickel, Ivy Yip, Jan Enkmann, Kye Shimizu, Pattie Maes, Sally Ahmed, Vincent Beermann.

Figure 1
Figure 1. Figure 1: Screenshots of the custom Android observation application. (a) The main dashboard showing data [PITH_FULL_IMAGE:figures/full_fig_p008_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Application usage patterns. (a) Number of sessions per application. Instagram, YouTube, and Facebook [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Median session duration for social media versus non-social media app sessions, computed per partici [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Perceived intention-usage gap explains regret better than session duration. (a) The effect of duration [PITH_FULL_IMAGE:figures/full_fig_p013_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Regret is higher when opportunity costs are salient: Day vs. night (a, c) and productivity drift (b, d). (a) [PITH_FULL_IMAGE:figures/full_fig_p015_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Across N=16 interviews, participants described nine ways timer-based interventions fail. They cluster [PITH_FULL_IMAGE:figures/full_fig_p020_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Participant exclusion flow from enrollment to the final analytic sample. [PITH_FULL_IMAGE:figures/full_fig_p029_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Co-outcome distributions. (a) Session meaningfulness ratings, with most sessions rated low to moderate. [PITH_FULL_IMAGE:figures/full_fig_p036_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Data collection overview. (a) Number of logged social media sessions per participant, ranging from 22 [PITH_FULL_IMAGE:figures/full_fig_p036_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Distribution of session-level regret ratings. (a) Histogram of all 1,445 sessions showing a slight positive [PITH_FULL_IMAGE:figures/full_fig_p037_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Within-person ROC curves across the three feature subsets: Smartwatch ( [PITH_FULL_IMAGE:figures/full_fig_p038_11.png] view at source ↗
read the original 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper reports results from a 7-day in-the-wild experience-sampling study with 21 participants yielding 1,445 social media sessions. Passive smartphone logging, Bangle.js 2 smartwatch data, pre- and post-session surveys, and exit interviews are used to predict regret. The three main claims are: (i) the gap between intended and actual use predicts regret more strongly than session duration (with duration's effect collapsing once intention is included); (ii) regret increases when sessions displace valued alternatives, especially at night or after productivity-app use; (iii) pre-session contextual features generalize across users while physiological signals provide person-specific predictive lift, supporting a two-layer JITAI architecture. Interview themes on scrolling-as-avoidance and time blindness are used to contextualize the quantitative patterns.

Significance. If the central regression results survive checks for self-report bias, the work advances HCI by treating regret (rather than screen time) as the ecologically valid target and by showing that low-cost consumer wearables can support in-the-wild, anticipatory intervention. The multi-modal design, combination of passive logging with experience sampling, and qualitative grounding are clear strengths. The study supplies concrete design implications beyond timer-based tools.

major comments (3)
  1. [Abstract and Results section on intention gap] Abstract and Results (intention-gap regression): the claim that the intention-use gap predicts regret far more strongly than duration, causing duration's apparent effect to collapse, is the paper's strongest and most load-bearing result. Because both the predictor (pre-session intended duration) and the outcome (post-session regret) are participant self-reports while actual duration is logged, the analysis must explicitly test for correlated measurement error or post-hoc rationalization; the manuscript should report survey timing, wording, any validation against objective proxies, and sensitivity analyses that partial out shared method variance.
  2. [Results section on displacement effects] Results (displacement analysis): the claim that regret is amplified when sessions displace a valued alternative (particularly at night and after productivity-app use) requires the operational definition of 'valued alternative,' the exact survey items used to elicit it, and the full regression specification including interaction terms and controls; without these details the interaction result cannot be evaluated for robustness.
  3. [Results section on model generalization] Results (generalization and physiological lift): the assertion that contextual features generalize while physiological signals add person-specific lift, supporting a two-layer architecture, must be accompanied by the precise cross-validation scheme (e.g., leave-one-participant-out), performance metrics (AUC/F1 with confidence intervals or standard errors), and a direct comparison of the two layers; with only 21 participants these numbers are essential to substantiate the generalization claim.
minor comments (2)
  1. [Methods] Methods: provide the exact wording and response scales of the pre-session intention and post-session regret items so that the experience-sampling protocol can be replicated.
  2. [Figures] Figures: ensure all regression plots include error bars or confidence bands and clearly label participant-level vs. aggregate lines.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments emphasizing methodological transparency. We address each point below and will incorporate the requested details and analyses in the revision.

read point-by-point responses

  1. Referee: [Abstract and Results section on intention gap] Abstract and Results (intention-gap regression): the claim that the intention-use gap predicts regret far more strongly than duration, causing duration's apparent effect to collapse, is the paper's strongest and most load-bearing result. Because both the predictor (pre-session intended duration) and the outcome (post-session regret) are participant self-reports while actual duration is logged, the analysis must explicitly test for correlated measurement error or post-hoc rationalization; the manuscript should report survey timing, wording, any validation against objective proxies, and sensitivity analyses that partial out shared method variance.

    Authors: We agree this is a load-bearing result and that self-report concerns merit explicit treatment. Pre-session intention was collected immediately before each session via ESM prompt; regret was collected immediately after. In revision we will add exact item wording, timing details, and sensitivity analyses that control for logged duration and test shared method variance. We will also note the limitation regarding possible post-hoc rationalization. revision: yes

  2. Referee: [Results section on displacement effects] Results (displacement analysis): the claim that regret is amplified when sessions displace a valued alternative (particularly at night and after productivity-app use) requires the operational definition of 'valued alternative,' the exact survey items used to elicit it, and the full regression specification including interaction terms and controls; without these details the interaction result cannot be evaluated for robustness.

    Authors: We will expand the Methods to define 'valued alternative' (post-session ESM item asking whether the session displaced a planned or otherwise valued activity) and quote the exact items. The revised Results will include the complete regression specification with all interaction terms (displacement × time-of-day, displacement × prior productivity-app use) and controls. revision: yes

  3. Referee: [Results section on model generalization] Results (generalization and physiological lift): the assertion that contextual features generalize while physiological signals add person-specific lift, supporting a two-layer architecture, must be accompanied by the precise cross-validation scheme (e.g., leave-one-participant-out), performance metrics (AUC/F1 with confidence intervals or standard errors), and a direct comparison of the two layers; with only 21 participants these numbers are essential to substantiate the generalization claim.

    Authors: We employed leave-one-participant-out cross-validation. The revision will report AUC and F1 (with SEs) for the context-only model versus the context-plus-physiology model, plus a direct comparison of the two layers. We acknowledge the modest participant count (n=21) but note the 1,445 sessions supply substantial within-person data for the person-specific layer. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical observational study with independent data patterns

full rationale

This paper reports an in-the-wild experience-sampling study combining passive smartphone logging, wearable sensors, and session-level surveys to examine statistical associations between contextual features, intention-actual use gap, duration, and post-session regret. No equations, derivations, or model specifications are described that reduce any prediction to a fitted parameter or self-reported quantity by construction. Central claims rest on measured data relationships rather than definitional identities, self-citation chains, or renamed empirical patterns. The analysis is self-contained against external benchmarks with no load-bearing self-referential steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on the reliability of self-reported intention and regret data collected via experience sampling; no free parameters or invented entities are described in the abstract.

axioms (1)
  • domain assumption Self-reported intention and regret ratings collected after each session accurately reflect participants' internal states without substantial recall bias or social-desirability effects
    All key predictors and the outcome variable are derived from these surveys.

pith-pipeline@v0.9.1-grok · 5795 in / 1183 out tokens · 24039 ms · 2026-06-27T15:14:48.081597+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

107 extracted references · 89 canonical work pages

  1. [1]

    Adler, Dror Ben-Zeev, Vincent W.-S

    Daniel A. Adler, Dror Ben-Zeev, Vincent W.-S. Tseng, John M. Kane, Rachel Brian, Andrew T. Campbell, Marta Hauser, Emily A. Scherer, and Tanzeem Choudhury. 2020. Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks.JMIR mHealth and uHealth8, 8 (2020), e19962. doi:10.2196/19962

    work page doi:10.2196/19962 2020

  2. [3]

    Griffiths, Daria J

    Cecilie Schou Andreassen, Joël Billieux, Mark D. Griffiths, Daria J. Kuss, Zsolt Demetrovics, Elvis Mazzoni, and Ståle Pallesen. 2016. The relationship between addictive use of social media and video games and symptoms of psychiatric disorders: A large-scale cross-sectional study.Psychology of Addictive Behaviors30, 2 (March 2016), 252–262. doi:10.1037/adb0000160

    work page doi:10.1037/adb0000160 2016

  3. [4]

    Android Developers. 2024. AccessibilityService. https://developer.android.com/reference/android/accessibilityservice/ AccessibilityService. Accessed: 2024

    2024

  4. [5]

    Android Developers. 2024. UsageStatsManager. https://developer.android.com/reference/android/app/usage/ UsageStatsManager. Accessed: 2024

    2024

  5. [6]

    Android Developers. 2024. WorkManager. https://developer.android.com/reference/androidx/work/WorkManager. Accessed: 2024

    2024

  6. [7]

    Adams, Md Mahbubur Rahman, Megan Battles Lau, Syed Monowar Hossain, William T

    Rambabu Bari, Rummana J. Adams, Md Mahbubur Rahman, Megan Battles Lau, Syed Monowar Hossain, William T. Riley, et al. 2020. Automated Detection of Stressful Conversations Using Wearable Physiological and Inertial Sensors. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies4, 4 (2020)

    2020

  7. [8]

    Samuel Battalio et al. 2021. Sense2Stop: A Micro-Randomized Trial Using Wearable Sensors to Optimize a Just-in- Time-Adaptive Stress Management Intervention for Smoking Relapse Prevention.Contemporary Clinical Trials109 (2021)

    2021

  8. [9]

    Baumeister, Kathleen D

    Roy F. Baumeister, Kathleen D. Vohs, and Dianne M. Tice. 2007. The Strength Model of Self-Control.Current Directions in Psychological Science16, 6 (2007), 351–355. doi:10.1111/j.1467-8721.2007.00534.x

    work page doi:10.1111/j.1467-8721.2007.00534.x 2007

  9. [10]

    Bayer, Ian A

    Joseph B. Bayer, Ian A. Anderson, and Robert S. Tokunaga. 2022. Building and Breaking Social Media Habits.Current Opinion in Psychology45 (2022), 101303. doi:10.1016/j.copsyc.2022.101303

    work page doi:10.1016/j.copsyc.2022.101303 2022

  10. [11]

    Berkman, Cendri A

    Elliot T. Berkman, Cendri A. Hutcherson, Jordan L. Livingston, Lauren E. Kahn, and Michael Inzlicht. 2017. Self-Control as Value-Based Choice.Current Directions in Psychological Science26, 5 (2017), 422–428. doi:10.1177/0963721417704394 , Vol. 1, No. 1, Article . Publication date: June 2026. 24 Ahmed, Enkmann, Shimizu, et. al

    work page doi:10.1177/0963721417704394 2017

  11. [13]

    Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology.Qualitative Research in Psychology 3, 2 (2006), 77–101. doi:10.1191/1478088706qp063oa

    work page doi:10.1191/1478088706qp063oa 2006

  12. [14]

    Virginia Braun and Victoria Clarke. 2019. Reflecting on reflexive thematic analysis.Qualitative Research in Sport, Exercise and Health11, 4 (2019), 589–597. doi:10.1080/2159676X.2019.1628806

    work page doi:10.1080/2159676x.2019.1628806 2019

  13. [15]

    Yekta Said Can, Niaz Chalabianloo, Deniz Ekiz, and Cem Ersoy. 2019. Continuous Stress Detection Using Wearable Sensors in Real Life: Algorithmic Programming Contest Case Study.Sensors19, 8 (2019), 1849. doi:10.3390/s19081849

    work page doi:10.3390/s19081849 2019

  14. [16]

    Hyunsung Cho, Daeun Choi, Donghwi Kim, Wan Ju Kang, Eun Kyoung Choe, and Sung-Ju Lee. 2021. Reflect, Not Regret: Understanding Regretful Smartphone Use with App Feature-Level Analysis.Proceedings of the ACM on Human-Computer Interaction5, CSCW2 (2021), 1–28. doi:10.1145/3479600

    work page doi:10.1145/3479600 2021

  15. [17]

    Terry Connolly and Marcel Zeelenberg. 2002. Regret in Decision Making.Current Directions in Psychological Science 11, 6 (2002), 212–216. doi:10.1111/1467-8721.00203

    work page doi:10.1111/1467-8721.00203 2002

  16. [18]

    Ludwig, and Elliot T

    Danielle Cosme, Rita M. Ludwig, and Elliot T. Berkman. 2019. Comparing Two Neurocognitive Models of Self-Control During Dietary Decisions.Social Cognitive and Affective Neuroscience14, 9 (2019), 957–966. doi:10.1093/scan/nsz068

    work page doi:10.1093/scan/nsz068 2019

  17. [19]

    Lenze, Michael S

    Ruixuan Dai, Chenyang Lu, Linda Yun, Eric J. Lenze, Michael S. Avidan, and Thomas Kannampallil. 2021. Comparing Stress Prediction Models Using Smartwatch Physiological Signals and Participant Self-Reports.Computer Methods and Programs in Biomedicine208 (2021), 106207. doi:10.1016/j.cmpb.2021.106207

    work page doi:10.1016/j.cmpb.2021.106207 2021

  18. [20]

    Duckworth, Tamar Szabó Gendler, and James J

    Angela L. Duckworth, Tamar Szabó Gendler, and James J. Gross. 2016. Situational Strategies for Self-Control. Perspectives on Psychological Science11, 1 (2016), 35–55. doi:10.1177/1745691615623247

    work page doi:10.1177/1745691615623247 2016

  19. [21]

    Epstein, Jennifer H

    Daniel A. Epstein, Jennifer H. Kang, Laura R. Pina, James Fogarty, and Sean A. Munson. 2016. Reconsidering the Device in the Drawer: Lapses as a Design Opportunity in Personal Informatics. InProceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp ’16). Association for Computing Machinery, New York, NY, USA...

    work page doi:10.1145/2971648.2971656 2016

  20. [22]

    Espruino. 2024. Bangle.js 2. https://www.espruino.com/Bangle.js2. Accessed: 2024

    2024

  21. [23]

    King, Pierre Maurage, José C

    Maèva Flayelle, Damien Brevers, Daniel L. King, Pierre Maurage, José C. Perales, and Joël Billieux. 2023. A Taxonomy of Technology Design Features That Promote Potentially Addictive Online Behaviours.Nature Reviews Psychology2, 3 (2023), 136–150. doi:10.1038/s44159-023-00153-4

    work page doi:10.1038/s44159-023-00153-4 2023

  22. [24]

    Freeyourgadget. 2024. Gadgetbridge. https://codeberg.org/Freeyourgadget/Gadgetbridge/. Accessed: 2024

    2024

  23. [25]

    Enrique Garcia-Ceja et al. 2018. Unobtrusive Assessment of Students’ Emotional Engagement during Lectures Using Electrodermal Activity Sensors.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2, 3 (2018). doi:10.1145/3264913

    work page doi:10.1145/3264913 2018

  24. [26]

    Christoph Gebhardt, Andreas Brombach, Tiffany Luong, Otmar Hilliges, and Christian Holz. 2024. Detecting Users’ Emotional States during Passive Social Media Use.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies8, 2 (May 2024), 1–30. doi:10.1145/3659606

    work page doi:10.1145/3659606 2024

  25. [27]

    Thomas Gilovich and Victoria Husted Medvec. 1995. The Experience of Regret: What, When, and Why.Psychological Review102, 2 (1995), 379–395. doi:10.1037/0033-295X.102.2.379

    work page doi:10.1037/0033-295x.102.2.379 1995

  26. [28]

    and Ulloaet, Hugo N

    David J. Grüning, Frederik Riedel, and Philipp Lorenz-Spreen. 2023. Directing smartphone use through the self-nudge app one sec.Proceedings of the National Academy of Sciences120, 8 (Feb. 2023), e2213114120. doi:10.1073/pnas. 2213114120

    work page doi:10.1073/pnas 2023

  27. [29]

    Longjie Guo, Yue Fu, Xiran Lin, Xuhai Xu, Yung-Ju Chang, and Alexis Hiniker. 2025. What Social Media Use Do People Regret? An Analysis of 34K Smartphone Screenshots with Multimodal LLM. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. ACM, Yokohama Japan, 1–23. doi:10.1145/3706598.3713724

    work page doi:10.1145/3706598.3713724 2025

  28. [30]

    Ross Harper and Joshua Southern. 2019. End-To-End Prediction of Emotion from Heartbeat Data Collected by a Consumer Fitness Tracker. InProceedings of the 8th International Conference on Affective Computing and Intelligent Interaction (ACII). 1–7. doi:10.1109/acii.2019.8925520

    work page doi:10.1109/acii.2019.8925520 2019

  29. [31]

    Hickey, Taryn Chalmers, Phillip Newton, Chin-Teng Lin, David Siber, Han Sean Leng, et al

    Brian A. Hickey, Taryn Chalmers, Phillip Newton, Chin-Teng Lin, David Siber, Han Sean Leng, et al. 2021. Smart Devices and Wearable Technologies to Detect and Monitor Mental Health Conditions and Stress: A Systematic Review. Sensors21, 10 (2021), 3461. doi:10.3390/s21103461

    work page doi:10.3390/s21103461 2021

  30. [32]

    Alexis Hiniker, Sungsoo (Ray) Hong, Tadayoshi Kohno, and Julie A. Kientz. 2016. MyTime: Designing and Evaluating an Intervention for Smartphone Non-Use. InProceedings of the 2016 CHI Conference on Human Factors in Computing Systems (CHI ’16). ACM, New York, NY, USA, 4746–4757. doi:10.1145/2858036.2858403

    work page doi:10.1145/2858036.2858403 2016

  31. [33]

    Baumeister, Georg Förster, and Kathleen D

    Wilhelm Hofmann, Roy F. Baumeister, Georg Förster, and Kathleen D. Vohs. 2012. Everyday Temptations: An Experience Sampling Study of Desire, Conflict, and Self-Control.Journal of Personality and Social Psychology102, 6 (2012), 1318–1335. doi:10.1037/a0026545

    work page doi:10.1037/a0026545 2012

  32. [34]

    Wilhelm Hofmann, Malte Friese, and Fritz Strack. 2009. Impulse and Self-Control From a Dual-Systems Perspective. Perspectives on Psychological Science4, 2 (2009), 162–176. doi:10.1111/j.1745-6924.2009.01116.x , Vol. 1, No. 1, Article . Publication date: June 2026. Before You Scroll Again: Predicting Regretful Social Media Sessions from In-the-Wild Context...

    work page doi:10.1111/j.1745-6924.2009.01116.x 2009

  33. [35]

    Hosmer and Stanley Lemeshow

    David W. Hosmer and Stanley Lemeshow. 2000.Applied Logistic Regression(2 ed.). John Wiley & Sons, New York. doi:10.1002/0471722146

    work page doi:10.1002/0471722146 2000

  34. [36]

    Karen Hovsepian, Mustafa al Absi, Emre Ertin, Thomas Kamarck, Motohiro Nakajima, and Santosh Kumar. 2015. cStress: Towards a Gold Standard for Continuous Stress Assessment in the Field Using Body Sensor Networks. Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing(2015), 493–504. doi:10.1145/2750858.2807526

    work page doi:10.1145/2750858.2807526 2015

  35. [37]

    Chiungjung Huang. 2022. A Meta-Analysis of the Problematic Social Media Use and Mental Health.International Journal of Social Psychiatry68, 1 (2022), 12–33. doi:10.1177/0020764020978434

    work page doi:10.1177/0020764020978434 2022

  36. [38]

    Werner, Julia L

    Michael Inzlicht, Kaitlyn M. Werner, Julia L. Briskin, and Brent W. Roberts. 2021. Integrating Models of Self-Regulation. Annual Review of Psychology72 (2021), 319–345. doi:10.1146/annurev-psych-061020-105721

    work page doi:10.1146/annurev-psych-061020-105721 2021

  37. [39]

    Natasha Jaques, Ognjen Rudovic, Sara Taylor, Akane Sano, and Rosalind Picard. 2017. Predicting Tomorrow’s Mood, Health, and Stress Level Using Personalized Multitask Learning and Domain Adaptation. InProceedings of IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing (Proceedings of Machine Learning Research, Vol. 66). PMLR, 17–33

    2017

  38. [40]

    Natasha Jaques, Sara Taylor, Asaph Azaria, Asma Ghandeharioun, Akane Sano, and Rosalind Picard. 2015. Predicting Students’ Happiness from Physiology, Phone, Mobility, and Behavioral Data. InProceedings of the 2015 International Conference on Affective Computing and Intelligent Interaction (ACII). 222–228. doi:10.1109/ACII.2015.7344575

    work page doi:10.1109/acii.2015.7344575 2015

  39. [41]

    Yaqi Jiang, Zhihao Yan, and Zeyang Yang. 2025. Losing Track of Time on TikTok? An Experimental Study of Short Video Users’ Time Distortion.Behavioral Sciences15, 7 (2025), 930. doi:10.3390/bs15070930

    work page doi:10.3390/bs15070930 2025

  40. [42]

    Nikoletta-Anna Kapogianni, Angeliki Sideraki, and Christos-Nikolaos Anagnostopoulos. 2025. Using Smartwatches in Stress Management, Mental Health, and Well-Being: A Systematic Review.Algorithms18, 7 (2025), 419. doi:10. 3390/a18070419

    2025

  41. [43]

    Inyeop Kim and Uichin Lee. 2024. Navigating User-System Gaps: Understanding User-Interactions in User-Centric Context-Aware Systems for Digital Well-being Intervention. InProceedings of the CHI Conference on Human Factors in Computing Systems. ACM, Honolulu HI USA, 1–15. doi:10.1145/3613904.3641979

    work page doi:10.1145/3613904.3641979 2024

  42. [44]

    Minhyung Kim, Inyeop Kim, and Uichin Lee. 2021. Beneficial Neglect: Instant Message Notification Handling Behaviors and Academic Performance.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies5, 1 (2021), 1–26. doi:10.1145/3448089

    work page doi:10.1145/3448089 2021

  43. [45]

    Minsam Ko, Subin Yang, Joonwon Lee, Christian Heizmann, Jinyoung Jeong, Uichin Lee, Daehee Shin, Koji Yatani, Junehwa Song, and Kyong-Mee Chung. 2015. NUGU: A Group-based Intervention App for Improving Self-Regulation of Limiting Smartphone Use. InProceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing (CSCW ’15). ...

    work page doi:10.1145/2675133.2675244 2015

  44. [46]

    Kotabe and Wilhelm Hofmann

    Hiroki P. Kotabe and Wilhelm Hofmann. 2015. On Integrating the Components of Self-Control.Perspectives on Psychological Science10, 5 (2015), 618–638. doi:10.1177/1745691615593382

    work page doi:10.1177/1745691615593382 2015

  45. [47]

    Spitzer, and Janet B

    Kurt Kroenke, Robert L. Spitzer, and Janet B. W. Williams. 2001. The PHQ-9: Validity of a brief depression severity measure.Journal of General Internal Medicine16, 9 (Sept. 2001), 606–613. doi:10.1046/j.1525-1497.2001.016009606.x

    work page doi:10.1046/j.1525-1497.2001.016009606.x 2001

  46. [48]

    Hansoo Lee, Taehyeon Park, Youngji Koh, Jae-Gil Lee, and Uichin Lee. 2025. Leveraging Smartphone Human Interaction Routine Behavior Task Mining and Modeling for Daily Stress Monitoring.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies9, 4 (2025), 1–45. doi:10.1145/3770644

    work page doi:10.1145/3770644 2025

  47. [49]

    Washington

    Joe Li and Peter Y. Washington. 2024. A Comparison of Personalized and Generalized Approaches to Emotion Recognition Using Consumer Wearable Devices: Machine Learning Study.JMIR AI3 (2024), e52171. doi:10.2196/52171

    work page doi:10.2196/52171 2024

  48. [50]

    Xuefei Lin et al . 2025. Beyond Detection: Towards Actionable Sensing Research in Clinical Mental Healthcare. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies(2025). doi:10.1145/3699755

    work page doi:10.1145/3699755 2025

  49. [51]

    Schultner, Allen Chang, Philippe N

    Björn Lindström, Martin Bellander, David T. Schultner, Allen Chang, Philippe N. Tobler, and David M. Amodio. 2021. A Computational Reward Learning Account of Social Media Engagement.Nature Communications12, 1 (2021), 1311. doi:10.1038/s41467-020-19607-x

    work page doi:10.1038/s41467-020-19607-x 2021

  50. [52]

    Adaptable Commitment Interfaces

    Kai Lukoff, Ulrik Lyngs, Karina Shirokova, Raveena Rao, Larry Tian, Himanshu Zade, Sean A. Munson, and Alexis Hiniker. 2023. SwitchTube: A Proof-of-Concept System Introducing “Adaptable Commitment Interfaces” as a Tool for Digital Wellbeing. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3544548.3580703

    work page doi:10.1145/3544548.3580703 2023

  51. [53]

    Kai Lukoff, Cissy Yu, Julie Kientz, and Alexis Hiniker. 2018. What Makes Smartphone Use Meaningful or Meaningless? Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies2, 1 (March 2018), 1–26. doi:10. 1145/3191754

    2018

  52. [54]

    Lundberg and Su-In Lee

    Scott M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. InAdvances in Neural Information Processing Systems, Vol. 30. 4765–4774

    2017

  53. [55]

    Ulrik Lyngs, Kai Lukoff, Petr Slovak, William Seymour, Helena Webb, Marina Jirotka, Jun Zhao, Max Van Kleek, and Nigel Shadbolt. 2020. ‘I Just Want to Hack Myself to Not Get Distracted’: Evaluating Design Interventions for , Vol. 1, No. 1, Article . Publication date: June 2026. 26 Ahmed, Enkmann, Shimizu, et. al Self-Control on Facebook. InProceedings of ...

    work page doi:10.1145/3313831.3376672 2020

  54. [56]

    Spada, and Alessio Vieno

    Claudia Marino, Natale Canale, Fiordalisa Melodia, Marcantonio M. Spada, and Alessio Vieno. 2021. The Overlap Between Problematic Smartphone Use and Problematic Social Media Use: A Systematic Review.Current Addiction Reports8, 4 (2021), 469–480. doi:10.1007/s40429-021-00398-0

    work page doi:10.1007/s40429-021-00398-0 2021

  55. [57]

    Lakmal Meegahapola, William Droz, Peter Kun, Amalia De Gotzen, Chaitanya Nutakki, Shyam Diber, George Rubin, et al. 2023. Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies6, 4 (2023). doi:10...

    work page doi:10.1145/3569483 2023

  56. [58]

    Abhinav Mehrotra, Veljko Pejović, Jo Vermeulen, Robert Hendley, and Mirco Musolesi. 2016. My Phone and Me: Understanding People’s Receptivity to Mobile Notifications. InProceedings of the 2016 CHI Conference on Human Factors in Computing Systems (CHI ’16). Association for Computing Machinery, New York, NY, USA, 1021–1032. doi:10.1145/2858036.2858566

    work page doi:10.1145/2858036.2858566 2016

  57. [59]

    Varun Mishra et al. 2021. Detecting Receptivity for mHealth Interventions in the Natural Environment.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies5, 2 (2021)

    2021

  58. [60]

    Smartphone Addiction

    Christian Montag, Elisa Wegmann, Rayna Sariyska, Zsolt Demetrovics, and Matthias Brand. 2021. How to Overcome Taxonomical Problems in the Study of Internet Use Disorders and What to Do with “Smartphone Addiction”?Journal of Behavioral Addictions9, 4 (2021), 908–914. doi:10.1556/2006.8.2019.59

    work page doi:10.1556/2006.8.2019.59 2021

  59. [61]

    D’Mello, Munmun De Choudhury, Gregory D

    Mehrab Bin Morshed, Koustuv Saha, Richard Li, Sidney K. D’Mello, Munmun De Choudhury, Gregory D. Abowd, and Thomas Plötz. 2019. Prediction of Mood Instability with Passive Sensing.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies3, 3 (2019). doi:10.1145/3351233

    work page doi:10.1145/3351233 2019

  60. [62]

    Inbal Nahum-Shani and Susan A. Murphy. 2025. Just-in-Time Adaptive Interventions: Where Are We Now and What Is Next?Annual Review of Psychology(Sept. 2025). doi:10.1146/annurev-psych-121024-044244

    work page doi:10.1146/annurev-psych-121024-044244 2025

  61. [64]

    Dey, and Xuhai "Orson" Xu

    Adiba Orzikulova, Han Xiao, Zhipeng Li, Yukang Yan, Yuntao Wang, Yuanchun Shi, Marzyeh Ghassemi, Sung- Ju Lee, Anind K. Dey, and Xuhai "Orson" Xu. 2024. Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention. InProceedings of the CHI Conference on Human Factors in Computing Systems. 1–20. doi:10.1145/3613904.3642747 arXiv:24...

    work page doi:10.1145/3613904.3642747 2024

  62. [65]

    Antti Oulasvirta, Tye Rattenbury, Lingyi Ma, and Eeva Raita. 2012. Habits Make Smartphone Use More Pervasive. Personal and Ubiquitous Computing16, 1 (2012), 105–114. doi:10.1007/s00779-011-0412-2

    work page doi:10.1007/s00779-011-0412-2 2012

  63. [66]

    Serguei V. S. Pakhomov, Paul D. Thuras, Raymond Finzel, Jerika Eppel, and Michael Kotlyar. 2020. Using consumer- wearable technology for remote assessment of physiological response to stress in the naturalistic environment.PLOS ONE15, 3 (2020), e0229942. doi:10.1371/journal.pone.0229942

    work page doi:10.1371/journal.pone.0229942 2020

  64. [67]

    Sungkyu Park, Marios Constantinides, Luca Maria Aiello, Daniele Quercia, and Paul van Gent. 2020. WellBeat: A Framework for Tracking Daily Well-Being Using Smartwatches.IEEE Internet Computing24, 5 (2020), 10–17. doi:10.1109/mic.2020.3017867

    work page doi:10.1109/mic.2020.3017867 2020

  65. [68]

    Veljko Pejović and Mirco Musolesi. 2014. InterruptMe: Designing Intelligent Prompting Mechanisms for Pervasive Applications. InProceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 897–908. doi:10.1145/2632048.2632062

    work page doi:10.1145/2632048.2632062 2014

  66. [69]

    Rosalind W. Picard. 1997.Affective Computing. MIT Press, Cambridge, MA

    1997

  67. [70]

    Picard, Elias Vyzas, and Jennifer Healey

    Rosalind W. Picard, Elias Vyzas, and Jennifer Healey. 2001. Toward Machine Emotional Intelligence: Analysis of Affective Physiological State.IEEE Transactions on Pattern Analysis and Machine Intelligence23, 10 (2001), 1175–1191. doi:10.1109/34.954607

    work page doi:10.1109/34.954607 2001

  68. [71]

    Juan Carlos Quiroz, Elena Geangu, and Min Hooi Yong. 2018. Emotion recognition using smart watch sensor data: Mixed-design study.JMIR Mental Health5, 3 (2018), e10153. doi:10.2196/10153

    work page doi:10.2196/10153 2018

  69. [72]

    Md Mafijul Islam Rashid et al. 2024. A Reproducible Stress Prediction Pipeline with Mobile Sensor Data.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies8, 3 (2024). doi:10.1145/3678578

    work page doi:10.1145/3678578 2024

  70. [73]

    Leonard Reinecke and Wilhelm Hofmann. 2016. Slacking Off or Winding Down? An Experience Sampling Study on the Drivers and Consequences of Media Use for Recovery versus Procrastination.Human Communication Research 42, 3 (2016), 441–461. doi:10.1111/hcre.12082

    work page doi:10.1111/hcre.12082 2016

  71. [74]

    Jan Ole Rixen, Luca-Maxim Meinhardt, Michael Glöckler, Marius-Lukas Ziegenbein, Anna Schlothauer, Mark Colley, Enrico Rukzio, and Jan Gugenheimer. 2023. The Loop and Reasons to Break It: Investigating Infinite Scrolling Behaviour in Social Media Applications and Reasons to Stop.Proceedings of the ACM on Human-Computer Interaction 7, MHCI, Article 228 (Sep...

    work page doi:10.1145/3604275 2023

  72. [75]

    Robinson and Kent C

    Terry E. Robinson and Kent C. Berridge. 2025. The Incentive-Sensitization Theory of Addiction 30 Years On.Annual Review of Psychology76 (2025), 29–58. doi:10.1146/annurev-psych-011624-024031

    work page doi:10.1146/annurev-psych-011624-024031 2025

  73. [76]

    Alberto Monge Roffarello and Luigi De Russis. 2023. Achieving Digital Wellbeing Through Digital Self-control Tools: A Systematic Review and Meta-analysis.ACM Transactions on Computer-Human Interaction30, 4 (Aug. 2023), 1–66. doi:10.1145/3571810

    work page doi:10.1145/3571810 2023

  74. [77]

    Mintra Ruensuk, Eunyong Cheon, Hwajung Hong, and Ian Oakley. 2020. How Do You Feel Online: Exploiting Smartphone Sensors to Detect Transitory Emotions during Social Media Use.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies4, 4 (Dec. 2020), 1–32. doi:10.1145/3432223

    work page doi:10.1145/3432223 2020

  75. [78]

    Daniel W. Russell. 1996. UCLA Loneliness Scale (Version 3): Reliability, Validity, and Factor Structure.Journal of Personality Assessment66, 1 (Feb. 1996), 20–40. doi:10.1207/s15327752jpa6601_2

    work page doi:10.1207/s15327752jpa6601_2 1996

  76. [79]

    Stanislaw Saganowski, Przemyslaw Kazienko, Maciej Dziezyc, Patrycja Jakimow, Joanna Komoszynska, Weronika Michalska, Anna Dutkowiak, Adam Polak, Adam Dziadek, and Michal Ujma. 2020. Consumer Wearables and Affective Computing for Wellbeing Support. InProceedings of the 17th EAI International Conference on Mobile and Ubiquitous Systems (MobiQuitous). 482–48...

    work page doi:10.1145/3448891.3450332 2020

  77. [80]

    Polak, and Przemyslaw Kazienko

    Stanislaw Saganowski, Bartosz Perz, Adam G. Polak, and Przemyslaw Kazienko. 2023. Emotion Recognition for Everyday Life Using Physiological Signals From Wearables: A Systematic Literature Review.IEEE Transactions on Affective Computing14, 3 (2023), 1876–1897. doi:10.1109/TAFFC.2022.3176135

    work page doi:10.1109/taffc.2022.3176135 2023

  78. [81]

    McHill, Andrew J

    Akane Sano, Sara Taylor, Andrew W. McHill, Andrew J. K. Phillips, Laura K. Barger, Elizabeth Klerman, and Rosalind Picard. 2018. Identifying Objective Physiological Markers and Modifiable Behaviors for Self-Reported Stress and Mental Health Status Using Wearable Sensors and Mobile Phones: Observational Study.Journal of Medical Internet Research20, 6 (2018...

    work page doi:10.2196/jmir.9410 2018

  79. [82]

    Zhanna Sarsenbayeva, Gabriele Marini, Niels van Berkel, Chu Luo, Weiwei Jiang, Kangning Yang, Greg Wadley, Tilman Dingler, Vassilis Kostakos, and Jorge Goncalves. 2020. Does smartphone use drive our emotions or vice versa? A causal analysis. InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems. ACM, 1–15. doi:10.1145/3313831.3376163

    work page doi:10.1145/3313831.3376163 2020

  80. [83]

    Berrenur Saylam and Özlem Durmaz İncel. 2023. Quantifying Digital Biomarkers for Well-Being: Stress, Anxiety, Positive and Negative Affect via Wearable Devices and Their Time-Based Predictions.Sensors23, 21 (2023), 8987. doi:10.3390/s23218987

    work page doi:10.3390/s23218987 2023

Showing first 80 references.