pith. machine review for the scientific record. sign in

arxiv: 2605.14360 · v1 · submitted 2026-05-14 · 💻 cs.HC · cs.CL

Recognition: 2 theorem links

· Lean Theorem

A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health Monitoring

Tamunotonye Harry , Johanna Hidalgo , Matthew Price , Yuanyuan Feng , Kathryn Stanton , Connie Tompkins , Peter Sheridan Dodds , Mikaela Irene Fudolig
show 2 more authors
Laura Bloomfield Christopher Danforth
Authors on Pith no claims yet

Pith reviewed 2026-05-15 02:25 UTC · model grok-4.3

classification 💻 cs.HC cs.CL
keywords affective textwearable sensingstudent healthNLP embeddingssleep qualityphysical activityheart rate variabilitylongitudinal monitoring
0
0 comments X

The pith

Ultra-brief text about daily concerns associates with measurable drops in physical activity and sleep quality on wearable sensors.

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

The paper tests whether short open-ended responses about what concerns students most can supply psychological context that wearable devices alone cannot recover. In data from 458 students tracked for a year with Oura rings, responses dominated by academic framing coincided with lower physical activity, while language reflecting emotional exhaustion coincided with worse sleep quality and reduced heart-rate variability. General pretrained language models extracted these links more reliably than models tuned to the student domain, and affective tone proved more predictive than the specific topics mentioned. The work shows that three-word prompts collected every two months can make passive sensor streams more interpretable without adding substantial user burden.

Core claim

Weeks dominated by academic concern framing in ultra-brief open-ended text were associated with lower physical activity; weeks characterized by emotional exhaustion language were associated with poorer sleep quality and lower heart rate variability. General pretrained embeddings outperformed domain-adapted models for most outcomes, while affective dimensions across methods consistently associated with sensor outcomes and zero-shot topic classification did not.

What carries the argument

Within-person mixed-effects models that relate NLP-derived features from ultra-brief concern text (dictionary, general embeddings, domain-adapted) to nine longitudinal sleep and activity metrics from wearable sensors.

If this is right

  • Academic concern language in brief text predicts reduced physical activity.
  • Emotional exhaustion language predicts poorer sleep quality and lower heart rate variability.
  • General pretrained embeddings deliver stronger associations than domain-adapted models for most outcomes.
  • Affective dimensions carry more signal than specific topical content identified by zero-shot classification.
  • Ultra-brief affective prompts can enrich the psychological interpretability of passive sensor data at low collection cost.

Where Pith is reading between the lines

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

  • The same brief-text approach could be tested in non-student working populations to check whether the academic and exhaustion patterns generalize.
  • Real-time monitoring systems might flag rising exhaustion language to prompt just-in-time support before wearable metrics deteriorate.
  • Because general embeddings worked best, the method may transfer across languages or cultures with little retraining.
  • Combining the text signal with other low-burden inputs such as location or calendar data could further strengthen the predictive models.

Load-bearing premise

The ultra-brief open-ended text responses validly capture the psychological states that actually drive the measured changes in sleep and activity without large self-report bias or unmeasured confounding.

What would settle it

A replication in which text responses are collected on a schedule independent of actual life events and no associations with the same wearable outcomes appear would falsify the central claim.

Figures

Figures reproduced from arXiv: 2605.14360 by Christopher Danforth, Connie Tompkins, Johanna Hidalgo, Kathryn Stanton, Laura Bloomfield, Matthew Price, Mikaela Irene Fudolig, Peter Sheridan Dodds, Tamunotonye Harry, Yuanyuan Feng.

Figure 1
Figure 1. Figure 1: Study design and analytical pipeline. Participants from LEMURS RCT ([ [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: t-SNE projection of RoBERTa-base embeddings for all 3,073 concern-present student-weeks (perplexity = 40), colored [PITH_FULL_IMAGE:figures/full_fig_p015_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Within-person wearable outcomes across two zoomed semantic neighborhoods of the RoBERTa-base embedding space [PITH_FULL_IMAGE:figures/full_fig_p017_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Daily step count (within-person 𝑧-score) across the academic/workload and emotional/relational semantic neigh￾borhoods of the RoBERTa-base embedding space. Each dot represents one student-week; color encodes the within-person 𝑧-scored step count (green = above average; red = below). Annotated concern texts illustrate the contrast between weeks with reduced activity (academic pressure, illness, recovery) an… view at source ↗
Figure 5
Figure 5. Figure 5: Within-person wearable outcomes across all five outcomes in the academic/workload cluster (top row) and emo [PITH_FULL_IMAGE:figures/full_fig_p038_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Incremental variance explained (Δ𝑅 2 ) by each NLP method above semester timing across nine wearable outcomes. Bars show the language block Δ𝑅 2 for SEANCE (blue), RoBERTa-base (orange), and MentalRoBERTa (green). Stars indicate the best-performing method per outcome. Negative values reflect suppression effects. All models restricted to concern-present waves (𝑁 = 2,982 sleep; 𝑁 = 2,966 activity). Proc. ACM… view at source ↗
read the original abstract

Wearable devices capture physiological and behavioral data with increasing fidelity, but the psychological context shaping these outcomes is difficult to recover from sensor data alone, limiting passive sensing utility for digital health. We examined whether ultra-brief naturalistic concern text could serve as a scalable complement to passive sensing. In a year-long study of 458 university students (3,610 person-waves) tracked with Oura rings, participants responded bimonthly to an open-ended prompt about what concerned them most; responses had a median length of three words. We compared dictionary-based, general pretrained, and domain-adapted NLP approaches using within-person mixed-effects models across nine sleep and physical activity outcomes. Weeks dominated by academic concern framing were associated with lower physical activity; weeks characterized by emotional exhaustion language were associated with poorer sleep quality and lower heart rate variability. General pretrained embeddings outperformed domain-adapted models for most outcomes, with domain adaptation showing relative advantage for autonomic outcomes. Zero-shot classification of concern topics produced no significant associations, while affective dimensions across all three methods were consistently associated with outcomes, indicating emotional register rather than topical content carries the signal. These findings offer design guidance: ultra-brief affective prompts enrich the psychological interpretability of passive physiological data at minimal burden.

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 findings from a year-long observational study of 458 university students (3,610 person-waves) wearing Oura rings, who provided bimonthly ultra-brief open-ended text responses (median length three words) about their primary concerns. Within-person mixed-effects models across nine sleep and physical activity outcomes show that academic-concern framing is associated with lower physical activity, emotional-exhaustion language with poorer sleep quality and lower heart-rate variability, and that general pretrained embeddings outperform domain-adapted models while affective dimensions (rather than zero-shot topic classifications) carry the signal.

Significance. If the associations prove robust, the work offers a low-burden, scalable complement to passive sensing that could improve psychological interpretability of wearable data in student-health applications. The comparative NLP results and emphasis on affective register over topical content supply concrete design implications for future digital-health systems.

major comments (3)
  1. Methods: exact per-wave sample sizes, exclusion criteria, and missing-data handling for the 3,610 person-waves are not reported, which is load-bearing for assessing power and bias in the within-person mixed-effects models run on nine outcomes.
  2. Results: effect sizes (e.g., standardized coefficients or marginal R²) for the reported associations are omitted, and no multiple-testing correction across the nine outcomes is described, undermining claims of consistent affective-dimension effects.
  3. Methods/Results: the central assumption that median-three-word responses validly index the psychological states causally shaping wearable outcomes lacks any concurrent validation against gold-standard scales; without this, the associations remain vulnerable to self-report bias or time-varying confounders such as exam periods.
minor comments (2)
  1. Abstract: the phrase 'bimonthly' should be clarified as every two months to avoid ambiguity with twice-monthly.
  2. The manuscript would benefit from a table summarizing model specifications (random effects, covariates, outcome definitions) for the nine outcomes.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for their constructive feedback. We address each major comment below and have revised the manuscript to improve methodological transparency and acknowledge study limitations.

read point-by-point responses

  1. Referee: Methods: exact per-wave sample sizes, exclusion criteria, and missing-data handling for the 3,610 person-waves are not reported, which is load-bearing for assessing power and bias in the within-person mixed-effects models run on nine outcomes.

    Authors: We agree these details are essential. The revised manuscript now includes a dedicated Methods subsection with exact per-wave sample sizes, explicit exclusion criteria (e.g., minimum response length and valid Oura data requirements), and missing-data handling via complete-case analysis with sensitivity checks. This information is summarized in an updated Table 1. revision: yes

  2. Referee: Results: effect sizes (e.g., standardized coefficients or marginal R²) for the reported associations are omitted, and no multiple-testing correction across the nine outcomes is described, undermining claims of consistent affective-dimension effects.

    Authors: We have added standardized coefficients and marginal R² values for all associations in the revised Results. We also applied Bonferroni correction across the nine outcomes and report both unadjusted and adjusted p-values to quantify effect sizes and address multiple comparisons. revision: yes

  3. Referee: Methods/Results: the central assumption that median-three-word responses validly index the psychological states causally shaping wearable outcomes lacks any concurrent validation against gold-standard scales; without this, the associations remain vulnerable to self-report bias or time-varying confounders such as exam periods.

    Authors: We acknowledge this limitation of the formative, low-burden design. The revised Discussion now explicitly discusses potential self-report bias and time-varying confounders such as exam periods, while clarifying that associations are correlational. No concurrent gold-standard scales were collected. revision: partial

standing simulated objections not resolved
  • The absence of concurrent validation against gold-standard psychological scales, which was not part of the original study protocol and cannot be added retroactively.

Circularity Check

0 steps flagged

No significant circularity in empirical observational study

full rationale

This is a purely empirical observational study that collects ultra-brief text responses and wearable data from 458 students, then fits standard within-person mixed-effects models to test associations between NLP-derived affective dimensions and nine sleep/activity outcomes. No derivations, equations, or predictions are presented; the central claims are direct statistical associations from the collected data. No self-citations are load-bearing for any derivation, no parameters are fitted and then renamed as predictions, and no ansatzes or uniqueness theorems are invoked. The work is self-contained against external benchmarks of empirical research.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on standard statistical assumptions for mixed-effects models and the validity of NLP representations for short affective text; no new free parameters, ad-hoc axioms, or invented entities are introduced beyond conventional data analysis practices.

axioms (1)
  • domain assumption Linear mixed-effects model assumptions (normality of residuals, independence within clusters) hold for within-person associations between text features and wearable outcomes
    Invoked implicitly for all reported associations across nine sleep and activity outcomes.

pith-pipeline@v0.9.0 · 5556 in / 1282 out tokens · 193341 ms · 2026-05-15T02:25:17.008797+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

76 extracted references · 76 canonical work pages · 2 internal anchors

  1. [1]

    Marco Altini and Hannu Kinnunen. 2021. The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring.Sensors21, 13 (2021), 4302. doi:10.3390/s21134302

    work page doi:10.3390/s21134302 2021

  2. [2]

    Razia Azen and David V. Budescu. 2003. The Dominance Analysis Approach for Comparing Predictors in Multiple Regression. Psychological Methods8, 2 (2003), 129–148. doi:10.1037/1082-989X.8.2.129

    work page doi:10.1037/1082-989x.8.2.129 2003

  3. [3]

    Scherer, Rui Wang, Haiyi Xie, and Andrew T

    Dror Ben-Zeev, Emily A. Scherer, Rui Wang, Haiyi Xie, and Andrew T. Campbell. 2015. Next-Generation Psychiatric Assessment: Using Smartphone Sensors to Monitor Behavior and Mental Health.Psychiatric Rehabilitation Journal38, 3 (2015), 218–226. doi:10.1037/ prj0000130

    work page 2015

  4. [4]

    Bradley and Peter J

    Margaret M. Bradley and Peter J. Lang. 1999.Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings. Technical Report C-1. Center for Research in Psychophysiology, University of Florida, Gainesville, FL

    work page 1999

  5. [5]

    David V. Budescu. 1993. Dominance Analysis: A New Approach to the Problem of Relative Importance of Predictors in Multiple Regression.Psychological Bulletin114, 3 (1993), 542–551. doi:10.1037/0033-2909.114.3.542

    work page doi:10.1037/0033-2909.114.3.542 1993

  6. [6]

    Ranganathan Chandrasekaran, Vipanchi Katthula, and Evangelos Moustakas. 2020. Patterns of use and key predictors for the use of wearable health care devices by US adults: insights from a national survey.Journal of medical Internet research22, 10 (2020), e22443

    work page 2020

  7. [7]

    Villalba, Janine M

    Prerna Chikersal, Afsaneh Doryab, Michael Tumminia, Daniella K. Villalba, Janine M. Dutcher, Xinwen Liu, Sheldon Cohen, Kasey G. Creswell, Jennifer Mankoff, J. David Creswell, Mayank Goel, and Anind K. Dey. 2021. Detecting Depression and Predicting Its Onset Using Longitudinal Symptoms Captured by Passive Sensing: A Machine Learning Approach with Robust F...

    work page doi:10.1145/3422821 2021

  8. [8]

    Copeland, Ellen McGinnis, Yang Bai, Zoe Adams, Hilary Nardone, Vinay Devadanam, Jeffrey Rettew, and Jim J

    William E. Copeland, Ellen McGinnis, Yang Bai, Zoe Adams, Hilary Nardone, Vinay Devadanam, Jeffrey Rettew, and Jim J. Hudziak

    work page

  9. [9]

    doi:10.1016/j.jaac.2020.08.466

    Impact of COVID-19 Pandemic on College Student Mental Health and Wellness.Journal of the American Academy of Child & Adolescent Psychiatry60, 1 (2021), 134–141.e2. doi:10.1016/j.jaac.2020.08.466

    work page doi:10.1016/j.jaac.2020.08.466 2021

  10. [10]

    Glen Coppersmith, Mark Dredze, and Craig Harman. 2014. Quantifying Mental Health Signals in Twitter. InProceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality. Association for Computational Linguistics, Baltimore, Maryland, USA, 51–60. doi:10.3115/v1/W14-3207

    work page doi:10.3115/v1/w14-3207 2014

  11. [11]

    Cornet and Richard J

    Victor P. Cornet and Richard J. Holden. 2018. Systematic Review of Smartphone-Based Passive Sensing for Health and Wellbeing. Journal of Biomedical Informatics77 (2018), 120–132. doi:10.1016/j.jbi.2017.12.008

    work page doi:10.1016/j.jbi.2017.12.008 2018

  12. [12]

    Crossley, Kristopher Kyle, and Danielle S

    Scott A. Crossley, Kristopher Kyle, and Danielle S. McNamara. 2017. Sentiment Analysis and Social Cognition Engine (SEANCE): An Automatic Tool for Sentiment, Social Cognition, and Social-Order Analysis.Behavior Research Methods49, 3 (2017), 803–821. doi:10.3758/s13428-016-0743-z

    work page doi:10.3758/s13428-016-0743-z 2017

  13. [13]

    Munmun De Choudhury, Michael Gamon, Scott Counts, and Eric Horvitz. 2013. Predicting Depression via Social Media. InProceedings of the International AAAI Conference on Web and Social Media (ICWSM), Vol. 7. 128–137. doi:10.1609/icwsm.v7i1.14432

    work page doi:10.1609/icwsm.v7i1.14432 2013

  14. [14]

    Behavioral Sleep Medicine 17(2), 124–136 (2019)

    Massimiliano de Zambotti, Leonardo Rosas, Ian M. Colrain, and Fiona C. Baker. 2019. The Sleep of the Ring: Comparison of the ¯OURA Sleep Tracker Against Polysomnography.Behavioral Sleep Medicine17, 2 (2019), 124–136. doi:10.1080/15402002.2017.1300587

    work page doi:10.1080/15402002.2017.1300587 2019

  15. [15]

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. InProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). Association for Computational Linguistics, Mi...

    work page doi:10.18653/v1/n19-1423 2019

  16. [16]

    Facebook language predicts depression in medical records

    Johannes C. Eichstaedt, Robert J. Smith, Raina M. Merchant, Lyle H. Ungar, Patrick Crutchley, Daniel Preoţiuc-Pietro, David A. Asch, and H. Andrew Schwartz. 2018. Facebook Language Predicts Depression in Medical Records.Proceedings of the National Academy of Sciences115, 44 (2018), 11203–11208. doi:10.1073/pnas.1802331115

    work page doi:10.1073/pnas.1802331115 2018

  17. [17]

    Galambos, Andrea L

    Nancy L. Galambos, Andrea L. Dalton, and Jennifer L. Maggs. 2009. Losing Sleep Over It: Daily Variation in Sleep Quantity and Quality in Canadian Students’ First Semester of University.Journal of Research on Adolescence19, 4 (2009), 741–761. doi:10.1111/j.1532- 7795.2009.00618.x

    work page doi:10.1111/j.1532- 2009

  18. [18]

    Nuno Gomes, Matilde Pato, André Ribeiro Lourenço, and Nuno Datia. 2023. A Survey on Wearable Sensors for Mental Health Monitoring. Sensors23, 3 (2023), 1330. doi:10.3390/s23031330

    work page doi:10.3390/s23031330 2023

  19. [19]

    James J. Gross. 2002. Emotion Regulation: Affective, Cognitive, and Social Consequences.Psychophysiology39, 3 (2002), 281–291. doi:10.1017/S0048577201393198

    work page doi:10.1017/s0048577201393198 2002

  20. [20]

    Yaden, Margaret L

    Sharath Chandra Guntuku, David B. Yaden, Margaret L. Kern, Lyle H. Ungar, and Johannes C. Eichstaedt. 2017. Detecting Depression and Mental Illness on Social Media: An Integrative Review.Current Opinion in Behavioral Sciences18 (2017), 43–49. doi:10.1016/j.cobeha. 2017.07.005

    work page doi:10.1016/j.cobeha 2017

  21. [21]

    Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks. InProceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8342–8360. doi:10.18653/v1/2020.ac...

    work page doi:10.18653/v1/2020.acl-main.740 2020

  22. [22]

    Harari, Sandrine R

    Gabriella M. Harari, Sandrine R. Müller, Min S. H. Aung, and Peter J. Rentfrow. 2017. Smartphone Sensing Methods for Studying Behavior in Everyday Life.Current Opinion in Behavioral Sciences18 (2017), 83–90. doi:10.1016/j.cobeha.2017.07.018

    work page doi:10.1016/j.cobeha.2017.07.018 2017

  23. [23]

    Allison G. Harvey. 2002. A Cognitive Model of Insomnia.Behaviour Research and Therapy40, 8 (2002), 869–893. doi:10.1016/S0005- 7967(01)00061-4

    work page doi:10.1016/s0005- 2002

  24. [24]

    Heron, Robin S

    Kristin E. Heron, Robin S. Everhart, Susan M. McHale, and Joshua M. Smyth. 2017. Using Mobile-Technology-Based Ecological Momentary Assessment (EMA) Methods with Youth: A Systematic Review and Recommendations.Journal of Pediatric Psychology42, 10 (2017), 1087–1107. doi:10.1093/jpepsy/jsx078

    work page doi:10.1093/jpepsy/jsx078 2017

  25. [25]

    Minqing Hu and Bing Liu. 2004. Mining and Summarizing Customer Reviews. InProceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Seattle, WA, USA, 168–177. doi:10.1145/1014052.1014073

    work page doi:10.1145/1014052.1014073 2004

  26. [26]

    Kit Huckvale, Svetha Venkatesh, and Helen Christensen. 2019. Toward Clinical Digital Phenotyping: A Timely Opportunity to Consider Purpose, Quality, and Safety.npj Digital Medicine2 (2019), 88. doi:10.1038/s41746-019-0166-1

    work page doi:10.1038/s41746-019-0166-1 2019

  27. [27]

    Jacobson, Berta Summers, and Sabine Wilhelm

    Nicholas C. Jacobson, Berta Summers, and Sabine Wilhelm. 2020. Digital Biomarkers of Social Anxiety Severity: Digital Phenotyping Using Passive Smartphone Sensors.Journal of Medical Internet Research22, 5 (2020), e16875. doi:10.2196/16875

    work page doi:10.2196/16875 2020

  28. [28]

    Shaoxiong Ji, Tianlin Zhang, Luna Ansari, Jie Fu, Prayag Tiwari, and Erik Cambria. 2022. MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare. InProceedings of the Thirteenth Language Resources and Evaluation Conference (LREC). European Language Resources Association, Marseille, France, 7184–7190

    work page 2022

  29. [29]

    Kiecolt-Glaser, Lynanne McGuire, Theodore F

    Janice K. Kiecolt-Glaser, Lynanne McGuire, Theodore F. Robles, and Ronald Glaser. 2002. Emotions, Morbidity, and Mortality: New Perspectives from Psychoneuroimmunology.Annual Review of Psychology53 (2002), 83–107. doi:10.1146/annurev.psych.53.100901.135217

    work page doi:10.1146/annurev.psych.53.100901.135217 2002

  30. [30]

    Elisabet Kristiansson, Jan Fridolfsson, Daniel Arvidsson, Agneta Holmång, Mats Börjesson, and Ulrika Andersson-Hall. 2023. Validation of Oura Ring Energy Expenditure and Steps in Laboratory and Free-Living.BMC Medical Research Methodology23 (2023), 50. doi:10. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., Vol. 1, No. 1, Article 1. Publication dat...

    work page 2023

  31. [31]

    Holly Krohn, Jerry Guintivano, Rachel Frische, Jamie Steed, Hannah Rackers, and Samantha Meltzer-Brody. 2022. App-Based Ecological Momentary Assessment to Enhance Clinical Care for Postpartum Depression: Pilot Acceptability Study.JMIR Formative Research6, 3 (2022), e28081. doi:10.2196/28081

    work page doi:10.2196/28081 2022

  32. [32]

    How Does Fitbit Measure Brainwaves

    Zilu Liang and Bernd Ploderer. 2020. “How Does Fitbit Measure Brainwaves”: A Qualitative Study into the Credibility of Sleep-Tracking Technologies.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies4, 1 (2020), 1–29. doi:10.1145/3380994

    work page doi:10.1145/3380994 2020

  33. [33]

    Lattie, and Daniel Eisenberg

    Sarah Ketchen Lipson, Emily G. Lattie, and Daniel Eisenberg. 2019. Increased Rates of Mental Health Service Utilization by U.S. College Students: 10-Year Population-Level Trends (2007–2017).Psychiatric Services70, 1 (2019), 60–63. doi:10.1176/appi.ps.201800332

    work page doi:10.1176/appi.ps.201800332 2019

  34. [34]

    Eichstaedt, Chris J

    Tony Liu, Jonah Meyerhoff, Johannes C. Eichstaedt, Chris J. Karr, Susan M. Kaiser, Konrad P. Kording, David C. Mohr, and Lyle H. Ungar

    work page

  35. [35]

    doi:10.1016/j.jad.2021.12.048

    The Relationship between Text Message Sentiment and Self-Reported Depression.Journal of Affective Disorders302 (2022), 7–14. doi:10.1016/j.jad.2021.12.048

    work page doi:10.1016/j.jad.2021.12.048 2022

  36. [36]

    Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach.arXiv preprint arXiv:1907.11692(2019)

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  37. [37]

    Lund, Brian D

    Hannah G. Lund, Brian D. Reider, Annie B. Whiting, and J. Roxanne Prichard. 2010. Sleep Patterns and Predictors of Disturbed Sleep in a Large Population of College Students.Journal of Adolescent Health46, 2 (2010), 124–132. doi:10.1016/j.jadohealth.2009.06.016

    work page doi:10.1016/j.jadohealth.2009.06.016 2010

  38. [38]

    Lakmal Meegahapola, William Droz, Peter Kun, Amalia de Götzen, Chaitanya Nutakki, Shyam Diwakar, Salvador Ruiz Correa, Donglei Song, Hao Xu, Miriam Bidoglia, George Gaskell, Altangerel Chagnaa, Amarsanaa Ganbold, Tsolmon Zundui, Carlo Caprini, Daniele Miorandi, Alethia Hume, Jose Luis Zarza, Luca Cernuzzi, Ivano Bison, Marcelo Rodas Britez, Matteo Busso, ...

    work page doi:10.1145/3569483 2023

  39. [39]

    Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space.arXiv preprint arXiv:1301.3781(2013)

    work page internal anchor Pith review Pith/arXiv arXiv 2013

  40. [40]

    Mohammad and Peter D

    Saif M. Mohammad and Peter D. Turney. 2013. Crowdsourcing a Word-Emotion Association Lexicon.Computational Intelligence29, 3 (2013), 436–465. doi:10.1111/j.1467-8640.2012.00460.x

    work page doi:10.1111/j.1467-8640.2012.00460.x 2013

  41. [41]

    Mohr, Mi Zhang, and Stephen M

    David C. Mohr, Mi Zhang, and Stephen M. Schueller. 2017. Personal Sensing: Understanding Mental Health Using Ubiquitous Sensors and Machine Learning.Annual Review of Clinical Psychology13 (2017), 23–47. doi:10.1146/annurev-clinpsy-032816-044949

    work page doi:10.1146/annurev-clinpsy-032816-044949 2017

  42. [42]

    Debbie S Moskowitz and Simon N Young. 2006. Ecological momentary assessment: what it is and why it is a method of the future in clinical psychopharmacology.Journal of Psychiatry and Neuroscience31, 1 (2006), 13–20

    work page 2006

  43. [43]

    Smith, Bonnie J

    Inbal Nahum-Shani, Shawna N. Smith, Bonnie J. Spring, Linda M. Collins, Katie Witkiewitz, Ambuj Tewari, and Susan A. Murphy. 2018. Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support.Annals of Behavioral Medicine52, 6 (2018), 446–462. doi:10.1007/s12160-016-9830-8

    work page doi:10.1007/s12160-016-9830-8 2018

  44. [44]

    Shinichi Nakagawa and Holger Schielzeth. 2013. A General and Simple Method for Obtaining 𝑅2 from Generalized Linear Mixed-Effects Models.Methods in Ecology and Evolution4, 2 (2013), 133–142. doi:10.1111/j.2041-210x.2012.00261.x

    work page doi:10.1111/j.2041-210x.2012.00261.x 2013

  45. [45]

    Huckins, Courtney Rogers, Meghan L

    Subigya Nepal, Wenjun Liu, Arvind Pillai, Weichen Wang, Vlado Vojdanovski, Jeremy F. Huckins, Courtney Rogers, Meghan L. Meyer, and Andrew T. Campbell. 2024. Capturing the College Experience: A Four-Year Mobile Sensing Study of Mental Health, Resilience and Behavior of College Students during the Pandemic.Proceedings of the ACM on Interactive, Mobile, Wea...

    work page doi:10.1145/3643501 2024

  46. [46]

    Nobles, Jeffrey J

    Alicia L. Nobles, Jeffrey J. Glenn, Kamran Kowsari, Bethany A. Teachman, and Laura E. Barnes. 2018. Identification of Imminent Suicide Risk Among Young Adults Using Text Messages. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). ACM, Article 413, 11 pages. doi:10.1145/3173574.3173987

    work page doi:10.1145/3173574.3173987 2018

  47. [47]

    Wisco, and Sonja Lyubomirsky

    Susan Nolen-Hoeksema, Blair E. Wisco, and Sonja Lyubomirsky. 2008. Rethinking Rumination.Perspectives on Psychological Science3, 5 (2008), 400–424. doi:10.1111/j.1745-6924.2008.00088.x

    work page doi:10.1111/j.1745-6924.2008.00088.x 2008

  48. [48]

    Pennebaker, Matthias R

    James W. Pennebaker, Matthias R. Mehl, and Kate G. Niederhoffer. 2003. Psychological Aspects of Natural Language Use: Our Words, Our Selves.Annual Review of Psychology54 (2003), 547–577. doi:10.1146/annurev.psych.54.101601.145041

    work page doi:10.1146/annurev.psych.54.101601.145041 2003

  49. [49]

    Ellis, Sally Andrews, and Adam Joinson

    Lukasz Piwek, David A. Ellis, Sally Andrews, and Adam Joinson. 2016. The Rise of Consumer Health Wearables: Promises and Barriers. PLoS Medicine13, 2 (2016), e1001953. doi:10.1371/journal.pmed.1001953

    work page doi:10.1371/journal.pmed.1001953 2016

  50. [50]

    Matthew Price, Johanna E Hidalgo, Yoshi M Bird, Laura SP Bloomfield, Casey Buck, Janine Cerutti, Peter Sheridan Dodds, Mikaela Irene Fudolig, Rachel Gehman, Marc Hickok, et al. 2023. A Large Clinical Trial to Improve Well-Being During the Transition to College Using Wearables: The Lived Experiences Measured Using Rings Study.Contemporary Clinical Trials13...

    work page doi:10.1016/j.cct.2023 2023

  51. [51]

    Andrew G Reece and Christopher M Danforth. 2017. Instagram photos reveal predictive markers of depression.EPJ Data Science6, 1 (2017), 15

    work page 2017

  52. [52]

    Andrew G Reece, Andrew J Reagan, Katharina LM Lix, Peter Sheridan Dodds, Christopher M Danforth, and Ellen J Langer. 2017. Forecasting the onset and course of mental illness with Twitter data.Scientific reports7, 1 (2017), 13006. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., Vol. 1, No. 1, Article 1. Publication date: January 2026. A Formative St...

    work page 2017

  53. [53]

    Philip Resnik, William Armstrong, Leonardo Claudino, Thang Nguyen, Viet-An Nguyen, and Jordan Boyd-Graber. 2015. Beyond LDA: Exploring Supervised Topic Modeling for Depression-Related Language in Twitter. InProceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality (CLPsych). Associatio...

    work page doi:10.3115/v1/w15-1212 2015

  54. [54]

    John Rooksby, Mattias Rost, Alistair Morrison, and Matthew Chalmers. 2014. Personal Tracking as Lived Informatics. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 1163–1172. doi:10.1145/2556288.2557039

    work page doi:10.1145/2556288.2557039 2014

  55. [55]

    Schleider, Mallory L

    Jessica L. Schleider, Mallory L. Dobias, Jenna Y. Sung, Emma Mumper, and Michael C. Mullarkey. 2020. Acceptability and Utility of an Open-Access, Online Single-Session Intervention Platform for Adolescent Mental Health.JMIR Mental Health7, 6 (2020), e20513. doi:10.2196/20513

    work page doi:10.2196/20513 2020

  56. [56]

    Schleider and John R

    Jessica L. Schleider and John R. Weisz. 2017. Little Treatments, Promising Effects? Meta-Analysis of Single-Session Interventions for Youth Psychiatric Problems.Journal of the American Academy of Child & Adolescent Psychiatry56, 2 (2017), 107–115. doi:10.1016/j.jaac. 2016.11.007

    work page doi:10.1016/j.jaac 2017

  57. [57]

    Sefidgar, Woosuk Seo, Kevin S

    Yasaman S. Sefidgar, Woosuk Seo, Kevin S. Kuehn, Tim Althoff, Anne Browning, Eve Riskin, Paula S. Nurius, Anind K. Dey, and Jennifer Mankoff. 2019. Passively-Sensed Behavioral Correlates of Discrimination Events in College Students.Proceedings of the ACM on Human-Computer Interaction3, CSCW (2019), 1–29. doi:10.1145/3359216

    work page doi:10.1145/3359216 2019

  58. [58]

    Md Mobashir Hasan Shandhi, Karnika Singh, Natasha Janson, Perisa Ashar, Geetika Singh, Baiying Lu, D Sunshine Hillygus, Jennifer M Maddocks, and Jessilyn P Dunn. 2024. Assessment of ownership of smart devices and the acceptability of digital health data sharing. NPJ digital medicine7, 1 (2024), 44

    work page 2024

  59. [59]

    Stone, and Michael R

    Saul Shiffman, Arthur A. Stone, and Michael R. Hufford. 2008. Ecological Momentary Assessment.Annual Review of Clinical Psychology 4 (2008), 1–32. doi:10.1146/annurev.clinpsy.3.022806.091415

    work page doi:10.1146/annurev.clinpsy.3.022806.091415 2008

  60. [60]

    Odonkor, Jonathan K

    Matthew Smuck, Charles A. Odonkor, Jonathan K. Wilt, Nicolas Schmidt, and Michael A. Swiernik. 2021. The Emerging Clinical Role of Wearables: Factors for Successful Implementation in Healthcare.npj Digital Medicine4, 1 (2021), 45. doi:10.1038/s41746-021-00418-3

    work page doi:10.1038/s41746-021-00418-3 2021

  61. [61]

    Rachel Stanton, Peter Reaburn, Brenda Happell, Joanne Dodd, Justin Scanlan, Catherine McMahon, Emma White, and Kwong Fong. 2023. Wearable technologies for health research: Opportunities, limitations, and practical and conceptual considerations.Brain, Behavior, and Immunity – Health30 (2023), 100630. doi:10.1016/j.bbih.2023.100630

    work page doi:10.1016/j.bbih.2023.100630 2023

  62. [62]

    Stone and Saul Shiffman

    Arthur A. Stone and Saul Shiffman. 1994. Ecological Momentary Assessment (EMA) in Behavioral Medicine.Annals of Behavioral Medicine16, 3 (1994), 199–202. doi:10.1093/abm/16.3.199

    work page doi:10.1093/abm/16.3.199 1994

  63. [63]

    Stone, Dexter C

    Philip J. Stone, Dexter C. Dunphy, Marshall S. Smith, and Daniel M. Ogilvie. 1966.The General Inquirer: A Computer Approach to Content Analysis. MIT Press, Cambridge, MA

    work page 1966

  64. [64]

    Anne Marie Stupinski, Thayer Alshaabi, Michael V Arnold, Jane Lydia Adams, Joshua R Minot, Matthew Price, Peter Sheridan Dodds, and Christopher M Danforth. 2022. Quantifying changes in the Language used around Mental Health on Twitter over 10 years: Observational Study.JMIR mental health9, 3 (2022), e33685

    work page 2022

  65. [65]

    Yosephine Susanto, Erik Cambria, Bali Chandra Ng, and Amir Hussain. 2022. Ten Years of Sentic Computing.Cognitive Computation14 (2022), 5–23. doi:10.1007/s12559-021-09824-x

    work page doi:10.1007/s12559-021-09824-x 2022

  66. [66]

    Tausczik and James W

    Yla R. Tausczik and James W. Pennebaker. 2010. The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods. Journal of Language and Social Psychology29, 1 (2010), 24–54. doi:10.1177/0261927X09351676

    work page doi:10.1177/0261927x09351676 2010

  67. [67]

    Thayer, Fredrik Ahs, Mats Fredrikson, John J

    Julian F. Thayer, Fredrik Ahs, Mats Fredrikson, John J. Sollers, and Tor D. Wager. 2012. A Meta-Analysis of Heart Rate Variability and Neuroimaging Studies: Implications for Heart Rate Variability as a Marker of Stress and Health.Neuroscience and Biobehavioral Reviews 36, 2 (2012), 747–756. doi:10.1016/j.neubiorev.2011.11.009

    work page doi:10.1016/j.neubiorev.2011.11.009 2012

  68. [68]

    Trinh and Quoc V

    Trieu H. Trinh and Quoc V. Le. 2018. A Simple Method for Commonsense Reasoning.arXiv preprint arXiv:1806.02847(2018)

    work page arXiv 2018

  69. [69]

    Trull and Ulrich Ebner-Priemer

    Timothy J. Trull and Ulrich Ebner-Priemer. 2013. Ambulatory Assessment.Annual Review of Clinical Psychology9 (2013), 151–176. doi:10.1146/annurev-clinpsy-050212-185510

    work page doi:10.1146/annurev-clinpsy-050212-185510 2013

  70. [70]

    Trull and Ulrich W

    Timothy J. Trull and Ulrich W. Ebner-Priemer. 2020. Ambulatory Assessment in Psychopathology Research: A Review of Recommended Reporting Guidelines and Current Practices.Journal of Abnormal Psychology129, 1 (2020), 56–63. doi:10.1037/abn0000473

    work page doi:10.1037/abn0000473 2020

  71. [71]

    Campbell

    Rui Wang, Fanglin Chen, Zhenyu Chen, Tianxing Li, Gabriella Harari, Stefanie Tignor, Xia Zhou, Dror Ben-Zeev, and Andrew T. Campbell. 2014. StudentLife: Assessing Mental Health, Academic Performance and Behavioral Trends of College Students Using Smartphones. InProceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computin...

    work page doi:10.1145/2632048.2632054 2014

  72. [72]

    Fred Wen, Stefan Schneider, Arthur A

    Cheng K. Fred Wen, Stefan Schneider, Arthur A. Stone, and Donna Spruijt-Metz. 2017. Compliance with Mobile Ecological Momentary Assessment Protocols in Children and Adolescents: A Systematic Review and Meta-Analysis.Journal of Medical Internet Research19, 4 (2017), e132. doi:10.2196/jmir.6641

    work page doi:10.2196/jmir.6641 2017

  73. [73]

    Villalba, Janine M

    Xuhai Xu, Prerna Chikersal, Afsaneh Doryab, Daniella K. Villalba, Janine M. Dutcher, Michael J. Tumminia, Tim Althoff, Sheldon Cohen, Kasey G. Creswell, J. David Creswell, Jennifer Mankoff, and Anind K. Dey. 2019. Leveraging Routine Behavior and Contextually-Filtered Features for Depression Detection among College Students.Proceedings of the ACM on Intera...

    work page doi:10.1145/3351274 2019

  74. [74]

    Wenpeng Yin, Jamaal Hay, and Dan Roth. 2019. Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach. InProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, ...

    work page doi:10.18653/v1/d19-1404 2019

  75. [75]

    Zatzick, Sun-Mee Kang, W

    Douglas F. Zatzick, Sun-Mee Kang, W. Ladson Hinton, Rosemary H. Kelly, Donald M. Hilty, Carol E. Franz, Leanne Le, and Richard L. Kravitz. 2001. Posttraumatic Concerns: A Patient-Centered Approach to Outcome Assessment After Traumatic Physical Injury.Medical Care39, 4 (2001), 327–339. doi:10.1097/00005650-200104000-00004

    work page doi:10.1097/00005650-200104000-00004 2001

  76. [76]

    Yujie Zhu, Yonghao Long, Hailiang Wang, Kun Pyo Lee, Lie Zhang, and Stephen Jia Wang. 2024. Digital Behavior Change Intervention Designs for Habit Formation: Systematic Review.Journal of Medical Internet Research26 (2024), e54375. doi:10.2196/54375 Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., Vol. 1, No. 1, Article 1. Publication date: January 2...

    work page doi:10.2196/54375 2024