@inproceedings{zanwar-etal-2023-smhd,
title = "{SMHD}-{GER}: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in {G}erman",
author = "Zanwar, Sourabh and
Wiechmann, Daniel and
Qiao, Yu and
Kerz, Elma",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.113",
doi = "10.18653/v1/2023.findings-eacl.113",
pages = "1526--1541",
abstract = "Mental health problems are a challenge to our modern society, and their prevalence is predicted to increase worldwide. Recently, a surge of research has demonstrated the potential of automated detection of mental health conditions (MHC) through social media posts, with the ultimate goal of enabling early intervention and monitoring population-level health outcomes in real-time. Progress in this area of research is highly dependent on the availability of high-quality datasets and benchmark corpora. However, the publicly available datasets for understanding and modelling MHC are largely confined to the English language. In this paper, we introduce SMHD-GER (Self-Reported Mental Health Diagnoses for German), a large-scale, carefully constructed dataset for MHC detection built on high-precision patterns and the approach proposed for English. We provide benchmark models for this dataset to facilitate further research and conduct extensive experiments. These models leverage engineered (psycho-)linguistic features as well as BERT-German. We also examine nuanced patterns of linguistic markers characteristics of specific MHC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zanwar-etal-2023-smhd">
<titleInfo>
<title>SMHD-GER: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sourabh</namePart>
<namePart type="family">Zanwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Wiechmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elma</namePart>
<namePart type="family">Kerz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mental health problems are a challenge to our modern society, and their prevalence is predicted to increase worldwide. Recently, a surge of research has demonstrated the potential of automated detection of mental health conditions (MHC) through social media posts, with the ultimate goal of enabling early intervention and monitoring population-level health outcomes in real-time. Progress in this area of research is highly dependent on the availability of high-quality datasets and benchmark corpora. However, the publicly available datasets for understanding and modelling MHC are largely confined to the English language. In this paper, we introduce SMHD-GER (Self-Reported Mental Health Diagnoses for German), a large-scale, carefully constructed dataset for MHC detection built on high-precision patterns and the approach proposed for English. We provide benchmark models for this dataset to facilitate further research and conduct extensive experiments. These models leverage engineered (psycho-)linguistic features as well as BERT-German. We also examine nuanced patterns of linguistic markers characteristics of specific MHC.</abstract>
<identifier type="citekey">zanwar-etal-2023-smhd</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.113</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.113</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1526</start>
<end>1541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SMHD-GER: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in German
%A Zanwar, Sourabh
%A Wiechmann, Daniel
%A Qiao, Yu
%A Kerz, Elma
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F zanwar-etal-2023-smhd
%X Mental health problems are a challenge to our modern society, and their prevalence is predicted to increase worldwide. Recently, a surge of research has demonstrated the potential of automated detection of mental health conditions (MHC) through social media posts, with the ultimate goal of enabling early intervention and monitoring population-level health outcomes in real-time. Progress in this area of research is highly dependent on the availability of high-quality datasets and benchmark corpora. However, the publicly available datasets for understanding and modelling MHC are largely confined to the English language. In this paper, we introduce SMHD-GER (Self-Reported Mental Health Diagnoses for German), a large-scale, carefully constructed dataset for MHC detection built on high-precision patterns and the approach proposed for English. We provide benchmark models for this dataset to facilitate further research and conduct extensive experiments. These models leverage engineered (psycho-)linguistic features as well as BERT-German. We also examine nuanced patterns of linguistic markers characteristics of specific MHC.
%R 10.18653/v1/2023.findings-eacl.113
%U https://aclanthology.org/2023.findings-eacl.113
%U https://doi.org/10.18653/v1/2023.findings-eacl.113
%P 1526-1541
Markdown (Informal)
[SMHD-GER: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in German](https://aclanthology.org/2023.findings-eacl.113) (Zanwar et al., Findings 2023)
ACL