@inproceedings{xu-etal-2026-cnsocialdepress,
title = "{CNS}ocial{D}epress: A {C}hinese Social Media Dataset for Depression Risk Detection and Structured Analysis",
author = "Xu, Jinyuan and
Lan, Tian and
Yu, Xintao and
He, Xue and
Zhang, Hezhi and
Wang, Ying and
Valette, Mathieu and
Magistry, Pierre and
Li, Lei",
editor = {Kokkinakis, Dimitrios and
Themistocleous, Charalambos and
Dias, Ga{\"e}l and
Fraser, Kathleen C. and
{\"O}hman, Fredrik and
Pais, Sebasti{\~a}o},
booktitle = "Proceedings of the Sixth Resources and {P}rocess{I}ng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the {MENTAL}.ai consortium",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.rapid-1.8/",
doi = "10.63317/45bbx7jzw7i4",
pages = "82--105",
abstract = "Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce and largely focus on binary classification. To address this limitation, we release CNSocialDepress, a benchmark dataset for depression risk detection on Chinese social media. The dataset contains 44,178 posts from 233 users; psychological experts annotated 10,306 depression-related segments. CNSocialDepress provides binary risk labels along with structured, multidimensional psychological attributes, enabling interpretable and fine-grained analyses of depressive signals. Experimental results demonstrate the dataset{'}s utility across a range of NLP tasks, including structured psychological profiling and fine-tuning large language models for depression detection. Comprehensive evaluations highlight the dataset{'}s effectiveness and practical value for depression risk identification and psychological analysis, thereby providing insights for mental health applications tailored to Chinese-speaking populations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-cnsocialdepress">
<titleInfo>
<title>CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinyuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xintao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hezhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Valette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Magistry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the MENTAL.ai consortium</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Kokkinakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charalambos</namePart>
<namePart type="family">Themistocleous</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaël</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fredrik</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastião</namePart>
<namePart type="family">Pais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce and largely focus on binary classification. To address this limitation, we release CNSocialDepress, a benchmark dataset for depression risk detection on Chinese social media. The dataset contains 44,178 posts from 233 users; psychological experts annotated 10,306 depression-related segments. CNSocialDepress provides binary risk labels along with structured, multidimensional psychological attributes, enabling interpretable and fine-grained analyses of depressive signals. Experimental results demonstrate the dataset’s utility across a range of NLP tasks, including structured psychological profiling and fine-tuning large language models for depression detection. Comprehensive evaluations highlight the dataset’s effectiveness and practical value for depression risk identification and psychological analysis, thereby providing insights for mental health applications tailored to Chinese-speaking populations.</abstract>
<identifier type="citekey">xu-etal-2026-cnsocialdepress</identifier>
<identifier type="doi">10.63317/45bbx7jzw7i4</identifier>
<location>
<url>https://aclanthology.org/2026.rapid-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>82</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis
%A Xu, Jinyuan
%A Lan, Tian
%A Yu, Xintao
%A He, Xue
%A Zhang, Hezhi
%A Wang, Ying
%A Valette, Mathieu
%A Magistry, Pierre
%A Li, Lei
%Y Kokkinakis, Dimitrios
%Y Themistocleous, Charalambos
%Y Dias, Gaël
%Y Fraser, Kathleen C.
%Y Öhman, Fredrik
%Y Pais, Sebastião
%S Proceedings of the Sixth Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the MENTAL.ai consortium
%D 2026
%8 May
%I European Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F xu-etal-2026-cnsocialdepress
%X Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce and largely focus on binary classification. To address this limitation, we release CNSocialDepress, a benchmark dataset for depression risk detection on Chinese social media. The dataset contains 44,178 posts from 233 users; psychological experts annotated 10,306 depression-related segments. CNSocialDepress provides binary risk labels along with structured, multidimensional psychological attributes, enabling interpretable and fine-grained analyses of depressive signals. Experimental results demonstrate the dataset’s utility across a range of NLP tasks, including structured psychological profiling and fine-tuning large language models for depression detection. Comprehensive evaluations highlight the dataset’s effectiveness and practical value for depression risk identification and psychological analysis, thereby providing insights for mental health applications tailored to Chinese-speaking populations.
%R 10.63317/45bbx7jzw7i4
%U https://aclanthology.org/2026.rapid-1.8/
%U https://doi.org/10.63317/45bbx7jzw7i4
%P 82-105
Markdown (Informal)
[CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis](https://aclanthology.org/2026.rapid-1.8/) (Xu et al., RaPID 2026)
ACL
- Jinyuan Xu, Tian Lan, Xintao Yu, Xue He, Hezhi Zhang, Ying Wang, Mathieu Valette, Pierre Magistry, and Lei Li. 2026. CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis. In Proceedings of the Sixth Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the MENTAL.ai consortium, pages 82–105, Palma, Mallorca, Spain. European Language Resources Association (ELRA).