@inproceedings{sun-2026-digital,
title = "Digital Phenotyping Is Not a Shared Language: A Construct Audit of Public Mental-Health Datasets",
author = "Sun, Zefeng",
editor = "Wang, Zimu and
Jiang, Yiwen and
Shen, Yaling and
Zhao, Xiangyu and
Fong, Stephanie and
Sun, Xin and
Zhou, Yi and
Ji, Shaoxiong and
Desimone, Robert and
Nelson, Barnaby and
Dwyer, Dominic and
Ge, Zongyuan",
booktitle = "Proceedings of the 1st Workshop on Multimodal, Multilingual, and Multicultural Mental Health and Psychotherapy ({M}ulti{P}syche)",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.multipsyche-1.3/",
pages = "26--34",
ISBN = "979-8-89176-448-4",
abstract = "Public digital-phenotyping datasets share names for behaviors and mental-health outcomes while measuring them through different devices, processing rules, and instruments. We audit StudentLife, the College Experience Study (CES), CrossCheck, and Depresjon across feature definitions, temporal aggregation, population and study design, and outcome labels. Eight CES{--}CrossCheck daily correspondences yield raw-unit Hellinger distances from 0.104 for time in vehicle to 0.517 for unlock duration. Sensitivity analyses change the apparent similarity of several features: mobility distance rises from 0.148 to 0.307 after soft-outlier removal. Labels span PHQ-9, PHQ-2/PHQ-4, single-item and composite EMA, and clinician-rated MADRS. The effect audit separates between-person summaries from within-person variation. Between-person phone-feature correlations are small and uncertain; within-person stillness associations are 0.082 in CES and 0.053 in CrossCheck, with different outcome definitions. Depresjon shows lower mean activity in clinical cases than controls (d = {\ensuremath{-}}0.547). These findings make feature definition, preprocessing, label content, and statistical estimand explicit parts of cross-dataset evaluation. We provide field-level crosswalks, aggregate results, and reconstruction scripts for multimodal mental-health research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-2026-digital">
<titleInfo>
<title>Digital Phenotyping Is Not a Shared Language: A Construct Audit of Public Mental-Health Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zefeng</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal, Multilingual, and Multicultural Mental Health and Psychotherapy (MultiPsyche)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwen</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaling</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Fong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoxiong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Desimone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barnaby</namePart>
<namePart type="family">Nelson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominic</namePart>
<namePart type="family">Dwyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyuan</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-448-4</identifier>
</relatedItem>
<abstract>Public digital-phenotyping datasets share names for behaviors and mental-health outcomes while measuring them through different devices, processing rules, and instruments. We audit StudentLife, the College Experience Study (CES), CrossCheck, and Depresjon across feature definitions, temporal aggregation, population and study design, and outcome labels. Eight CES–CrossCheck daily correspondences yield raw-unit Hellinger distances from 0.104 for time in vehicle to 0.517 for unlock duration. Sensitivity analyses change the apparent similarity of several features: mobility distance rises from 0.148 to 0.307 after soft-outlier removal. Labels span PHQ-9, PHQ-2/PHQ-4, single-item and composite EMA, and clinician-rated MADRS. The effect audit separates between-person summaries from within-person variation. Between-person phone-feature correlations are small and uncertain; within-person stillness associations are 0.082 in CES and 0.053 in CrossCheck, with different outcome definitions. Depresjon shows lower mean activity in clinical cases than controls (d = \ensuremath-0.547). These findings make feature definition, preprocessing, label content, and statistical estimand explicit parts of cross-dataset evaluation. We provide field-level crosswalks, aggregate results, and reconstruction scripts for multimodal mental-health research.</abstract>
<identifier type="citekey">sun-2026-digital</identifier>
<location>
<url>https://aclanthology.org/2026.multipsyche-1.3/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>26</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Digital Phenotyping Is Not a Shared Language: A Construct Audit of Public Mental-Health Datasets
%A Sun, Zefeng
%Y Wang, Zimu
%Y Jiang, Yiwen
%Y Shen, Yaling
%Y Zhao, Xiangyu
%Y Fong, Stephanie
%Y Sun, Xin
%Y Zhou, Yi
%Y Ji, Shaoxiong
%Y Desimone, Robert
%Y Nelson, Barnaby
%Y Dwyer, Dominic
%Y Ge, Zongyuan
%S Proceedings of the 1st Workshop on Multimodal, Multilingual, and Multicultural Mental Health and Psychotherapy (MultiPsyche)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-448-4
%F sun-2026-digital
%X Public digital-phenotyping datasets share names for behaviors and mental-health outcomes while measuring them through different devices, processing rules, and instruments. We audit StudentLife, the College Experience Study (CES), CrossCheck, and Depresjon across feature definitions, temporal aggregation, population and study design, and outcome labels. Eight CES–CrossCheck daily correspondences yield raw-unit Hellinger distances from 0.104 for time in vehicle to 0.517 for unlock duration. Sensitivity analyses change the apparent similarity of several features: mobility distance rises from 0.148 to 0.307 after soft-outlier removal. Labels span PHQ-9, PHQ-2/PHQ-4, single-item and composite EMA, and clinician-rated MADRS. The effect audit separates between-person summaries from within-person variation. Between-person phone-feature correlations are small and uncertain; within-person stillness associations are 0.082 in CES and 0.053 in CrossCheck, with different outcome definitions. Depresjon shows lower mean activity in clinical cases than controls (d = \ensuremath-0.547). These findings make feature definition, preprocessing, label content, and statistical estimand explicit parts of cross-dataset evaluation. We provide field-level crosswalks, aggregate results, and reconstruction scripts for multimodal mental-health research.
%U https://aclanthology.org/2026.multipsyche-1.3/
%P 26-34
Markdown (Informal)
[Digital Phenotyping Is Not a Shared Language: A Construct Audit of Public Mental-Health Datasets](https://aclanthology.org/2026.multipsyche-1.3/) (Sun, MultiPsyche 2026)
ACL