{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T06:12:15Z","timestamp":1782799935190,"version":"3.54.5"},"reference-count":97,"publisher":"Association for Computing Machinery (ACM)","issue":"CSCW2","license":[{"start":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T00:00:00Z","timestamp":1695859200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2023,9,28]]},"abstract":"<jats:p>Getting training data for machine learning (ML) prediction of mental illness on social media data is labor intensive. To work around this, ML teams will extrapolate proxy signals, or alternative signs from data to evaluate illness status and create training datasets. However, these signals' validity has not been determined, whether signals align with important contextual factors, and how proxy quality impacts downstream model integrity. We use ML and qualitative methods to evaluate whether a popular proxy signal, diagnostic self-disclosure, produces a conceptually sound ML model of mental illness. Our findings identify major conceptual errors only seen through a qualitative investigation -- training data built from diagnostic disclosures encodes a narrow vision of diagnosis experiences that propagates into paradoxes in the downstream ML model. This gap is obscured by strong performance of the ML classifier (F1 = 0.91). We discuss the implications of conceptual gaps in creating training data for human-centered models, and make suggestions for improving research methods.<\/jats:p>","DOI":"10.1145\/3610181","type":"journal-article","created":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T15:54:10Z","timestamp":1696434850000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Contextual Gaps in Machine Learning for Mental Illness Prediction: The Case of Diagnostic Disclosures"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0620-0903","authenticated-orcid":false,"given":"Stevie","family":"Chancellor","sequence":"first","affiliation":[{"name":"University of Minnesota, Minneapolis, MN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4049-3589","authenticated-orcid":false,"given":"Jessica L.","family":"Feuston","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder, Boulder, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5370-6370","authenticated-orcid":false,"given":"Jayhyun","family":"Chang","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.clpsych-1.19"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.256"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594082"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2513"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702509"},{"key":"e_1_2_1_6_1","volume-title":"Don't quote me: reverse identification of research participants in social media studies. NPJ digital medicine","author":"Ayers John W","year":"2018","unstructured":"John W Ayers, Theodore L Caputi, Camille Nebeker, and Mark Dredze. 2018. Don't quote me: reverse identification of research participants in social media studies. NPJ digital medicine, Vol. 1, 1 (2018), 1--2."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23786"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1207\/S15327051HCI16234_05"},{"key":"e_1_2_1_9_1","volume-title":"Multi-task learning for mental health using social media text. arXiv preprint arXiv:1712.03538","author":"Benton Adrian","year":"2017","unstructured":"Adrian Benton, Margaret Mitchell, and Dirk Hovy. 2017. Multi-task learning for mental health using social media text. arXiv preprint arXiv:1712.03538 (2017)."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7956"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3134659"},{"key":"e_1_2_1_12_1","volume-title":"International handbook of internet research","author":"Bowker Geoffrey C","unstructured":"Geoffrey C Bowker, Karen Baker, Florence Millerand, and David Ribes. 2009. Toward information infrastructure studies: Ways of knowing in a networked environment. In International handbook of internet research. Springer, 97--117."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/380681"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-002411"},{"key":"e_1_2_1_15_1","volume-title":"Conference on fairness, accountability and transparency. PMLR, 77--91","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency. PMLR, 77--91."},{"key":"e_1_2_1_16_1","volume-title":"Towards Practices for Human-Centered Machine Learning. arXiv preprint arXiv:2203.00432","author":"Chancellor Stevie","year":"2022","unstructured":"Stevie Chancellor. 2022. Towards Practices for Human-Centered Machine Learning. arXiv preprint arXiv:2203.00432 (2022)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287587"},{"key":"e_1_2_1_18_1","volume-title":"Methods in predictive techniques for mental health status on social media: a critical review. NPJ digital medicine","author":"Chancellor Stevie","year":"2020","unstructured":"Stevie Chancellor and Munmun De Choudhury. 2020. Methods in predictive techniques for mental health status on social media: a critical review. NPJ digital medicine, Vol. 3, 1 (2020), 1--11."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174240"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025985"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2819963"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3026018"},{"key":"e_1_2_1_23_1","volume-title":"Brilliant imperfection: Grappling with cure","author":"Clare Eli","unstructured":"Eli Clare. 2017. Brilliant imperfection: Grappling with cure. Duke University Press."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3207"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1201"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v8i1.14574"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-0311"},{"key":"e_1_2_1_28_1","volume-title":"Watson","author":"Corrigan Patrick W.","year":"2004","unstructured":"Patrick W. Corrigan, Fred E. Markowitz, and Amy C. Watson. 2004. Structural levels of mental illness stigma and discrimination. Schizophrenia bulletin, Vol. 30, 3 (2004), 481--491."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.250"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502037"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13347-018-0336-0"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750511.2750515"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531602.2531675"},{"key":"e_1_2_1_34_1","volume-title":"Seventh international AAAI conference on weblogs and social media.","author":"Choudhury Munmun De","year":"2013","unstructured":"Munmun De Choudhury, Michael Gamon, Scott Counts, and Eric Horvitz. 2013. Predicting depression via social media. In Seventh international AAAI conference on weblogs and social media."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00338-7"},{"key":"e_1_2_1_36_1","volume-title":"Hilary Nicole, and Morgan Klaus Scheuerman.","author":"Denton Emily","year":"2020","unstructured":"Emily Denton, Alex Hanna, Razvan Amironesei, Andrew Smart, Hilary Nicole, and Morgan Klaus Scheuerman. 2020. Bringing the people back in: Contesting benchmark machine learning datasets. arXiv preprint arXiv:2007.07399 (2020)."},{"key":"e_1_2_1_37_1","volume-title":"Scale development: Theory and applications","author":"DeVellis Robert F","unstructured":"Robert F DeVellis and Carolyn T Thorpe. 2021. Scale development: Theory and applications. Sage publications."},{"key":"e_1_2_1_38_1","first-page":"591","article-title":"Diagnostic and statistical manual of mental disorders","volume":"21","author":"Fifth Edition","year":"2013","unstructured":"Fifth Edition et al. 2013. Diagnostic and statistical manual of mental disorders. Am Psychiatric Assoc, Vol. 21, 21 (2013), 591--643.","journal-title":"Am Psychiatric Assoc"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300364"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.15027"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/604045.604056"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555145"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274320"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300495"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392845"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/2056305118763366"},{"key":"e_1_2_1_47_1","volume-title":"History of madness","author":"Foucault Michel","unstructured":"Michel Foucault. 2013. History of madness. Routledge."},{"key":"e_1_2_1_48_1","volume-title":"The wounded storyteller: Body, illness, and ethics","author":"Frank Arthur W","unstructured":"Arthur W Frank. 2013. The wounded storyteller: Body, illness, and ethics. University of Chicago Press."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372862"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1177\/1461444818776611"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1177\/1049732310381388"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3415219"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.337"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359318"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1177\/08861099211062942"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531602.2531645"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449168"},{"key":"e_1_2_1_60_1","unstructured":"Dan Jurafsky. 2000. Speech & language processing. Pearson Education India."},{"key":"e_1_2_1_61_1","volume-title":"Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory. arXiv preprint arXiv:2205.05057","author":"Kaur Harmanpreet","year":"2022","unstructured":"Harmanpreet Kaur, Eytan Adar, Eric Gilbert, and Cliff Lampe. 2022a. Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory. arXiv preprint arXiv:2205.05057 (2022)."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517453"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376219"},{"key":"e_1_2_1_64_1","unstructured":"Arthur Kleinman. 2020. The illness narratives: Suffering healing and the human condition. Basic books."},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3110"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.04.008"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.4108\/eai.16-5-2016.2263336"},{"key":"e_1_2_1_68_1","volume-title":"I tweet passionately: Twitter users, context collapse, and the imagined audience. New media & society","author":"Marwick Alice E","year":"2011","unstructured":"Alice E Marwick and Danah Boyd. 2011. I tweet honestly, I tweet passionately: Twitter users, context collapse, and the imagined audience. New media & society, Vol. 13, 1 (2011), 114--133."},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359174"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0962-1849(05)80075-7"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1202"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2019.00013"},{"key":"e_1_2_1_73_1","unstructured":"Kayur Patel James Fogarty James A Landay and Beverly L Harrison. 2008. Examining Difficulties Software Developers Encounter in the Adoption of Statistical Machine Learning.. In AAAI. 1563--1566."},{"key":"e_1_2_1_74_1","volume-title":"Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing. 1185--1200","author":"Pater Jessica A","year":"2016","unstructured":"Jessica A Pater, Oliver L Haimson, Nazanin Andalibi, and Elizabeth D Mynatt. 2016. ?Hunger Hurts but Starving Works\" Characterizing the Presentation of Eating Disorders Online. In Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing. 1185--1200."},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300881"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0086191"},{"key":"e_1_2_1_77_1","volume-title":"The Fallacy of AI Functionality. In 2022 ACM Conference on Fairness, Accountability, and Transparency. 959--972","author":"Raji Inioluwa Deborah","year":"2022","unstructured":"Inioluwa Deborah Raji, I Elizabeth Kumar, Aaron Horowitz, and Andrew Selbst. 2022. The Fallacy of AI Functionality. In 2022 ACM Conference on Fairness, Accountability, and Transparency. 959--972."},{"key":"e_1_2_1_78_1","volume-title":"Squares: Supporting interactive performance analysis for multiclass classifiers","author":"Ren Donghao","year":"2016","unstructured":"Donghao Ren, Saleema Amershi, Bongshin Lee, Jina Suh, and Jason D Williams. 2016. Squares: Supporting interactive performance analysis for multiclass classifiers. IEEE transactions on visualization and computer graphics, Vol. 23, 1 (2016), 61--70."},{"key":"e_1_2_1_79_1","volume-title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks. arXiv preprint arXiv:2112.07475","author":"R\u00f6ttger Paul","year":"2021","unstructured":"Paul R\u00f6ttger, Bertie Vidgen, Dirk Hovy, and Janet B Pierrehumbert. 2021. Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks. arXiv preprint arXiv:2112.07475 (2021)."},{"key":"e_1_2_1_80_1","volume-title":"International Conference on Machine Learning. PMLR, 8346--8356","author":"Sagawa Shiori","year":"2020","unstructured":"Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, and Percy Liang. 2020. An investigation of why overparameterization exacerbates spurious correlations. In International Conference on Machine Learning. PMLR, 8346--8356."},{"key":"e_1_2_1_81_1","volume-title":"The coding manual for qualitative researchers","author":"Johnny Salda","unstructured":"Johnny Salda na. 2009. The coding manual for qualitative researchers. SAGE Publications."},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476058"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359246"},{"key":"e_1_2_1_85_1","volume-title":"Madness in Civilization: A Cultural History of Insanity, from the Bible to Freud, from the Madhouse to Modern Medicine","author":"Scull Andrew","unstructured":"Andrew Scull. 2015. Madness in Civilization: A Cultural History of Insanity, from the Bible to Freud, from the Madhouse to Modern Medicine. Princeton University Press. 432 pages."},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1093\/poq\/nfab018"},{"key":"e_1_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376783"},{"key":"e_1_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258465"},{"key":"e_1_2_1_89_1","volume-title":"The myth of mental illness: Foundations of a theory of personal conduct","author":"Szasz TS","unstructured":"TS Szasz. 1974. The myth of mental illness: Foundations of a theory of personal conduct. HarperPerennial."},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3398069"},{"key":"e_1_2_1_91_1","volume-title":"Delays in initial treatment contact after first onset of a mental disorder. Health services research","author":"Wang Philip S","year":"2004","unstructured":"Philip S Wang, Patricia A Berglund, Mark Olfson, and Ronald C Kessler. 2004. Delays in initial treatment contact after first onset of a mental disorder. Health services research, Vol. 39, 2 (2004), 393--416."},{"key":"e_1_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018706"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1073"},{"key":"e_1_2_1_94_1","volume-title":"Depression and self-harm risk assessment in online forums. arXiv preprint arXiv:1709.01848","author":"Yates Andrew","year":"2017","unstructured":"Andrew Yates, Arman Cohan, and Nazli Goharian. 2017. Depression and self-harm risk assessment in online forums. arXiv preprint arXiv:1709.01848 (2017)."},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3334480.3381828"},{"key":"e_1_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511146"},{"key":"e_1_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274463"}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610181","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:25:18Z","timestamp":1755750318000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,28]]},"references-count":97,"journal-issue":{"issue":"CSCW2","published-print":{"date-parts":[[2023,9,28]]}},"alternative-id":["10.1145\/3610181"],"URL":"https:\/\/doi.org\/10.1145\/3610181","relation":{},"ISSN":["2573-0142"],"issn-type":[{"value":"2573-0142","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,28]]},"assertion":[{"value":"2023-10-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}