@inproceedings{alqahtani-diab-2026-cross,
title = "Cross-Lingual and Cross-Genre Transfer for {A}rabic Schizophrenia Detection in Social Media",
author = "Alqahtani, Amal and
Diab, Mona",
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-1.9/",
pages = "105--117",
ISBN = "979-8-89176-448-4",
abstract = "Language-based schizophrenia detection has focused predominantly on English, leaving Arabic underrepresented in mental health NLP. We introduce an Arabic schizophrenia social media dataset (228 users, 228 controls; Cohen{'}s {\ensuremath{\kappa}}=0.76) and evaluate cross-lingual and cross-genre transfer across five primary settings and four reversed direction counterparts using XLM-RoBERTa-base, mBERT, and MARBERT. In-domain Arabic supervision yields the strongest performance, with MARBERT reaching 0.7706 macro-F1. In contrast, no primary transfer condition satisfies our criterion for robust transfer (macro-F1 {\ensuremath{>}} 0.50 and consistent performance across all three encoders). Reversed direction experiments suggest that genre transfer is directional: social to clinical transfer partially succeeds in the Arabic-only setting, whereas clinical to social transfer collapses. Results from translated clinical data further indicate that translation-based evaluation can introduce artifacts specific to encoder and direction. Overall, the findings support the need for native target language and target genre resources for reliable multilingual mental health evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alqahtani-diab-2026-cross">
<titleInfo>
<title>Cross-Lingual and Cross-Genre Transfer for Arabic Schizophrenia Detection in Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Alqahtani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</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>Language-based schizophrenia detection has focused predominantly on English, leaving Arabic underrepresented in mental health NLP. We introduce an Arabic schizophrenia social media dataset (228 users, 228 controls; Cohen’s \ensuremathąppa=0.76) and evaluate cross-lingual and cross-genre transfer across five primary settings and four reversed direction counterparts using XLM-RoBERTa-base, mBERT, and MARBERT. In-domain Arabic supervision yields the strongest performance, with MARBERT reaching 0.7706 macro-F1. In contrast, no primary transfer condition satisfies our criterion for robust transfer (macro-F1 \ensuremath> 0.50 and consistent performance across all three encoders). Reversed direction experiments suggest that genre transfer is directional: social to clinical transfer partially succeeds in the Arabic-only setting, whereas clinical to social transfer collapses. Results from translated clinical data further indicate that translation-based evaluation can introduce artifacts specific to encoder and direction. Overall, the findings support the need for native target language and target genre resources for reliable multilingual mental health evaluation.</abstract>
<identifier type="citekey">alqahtani-diab-2026-cross</identifier>
<location>
<url>https://aclanthology.org/2026.multipsyche-1.9/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>105</start>
<end>117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual and Cross-Genre Transfer for Arabic Schizophrenia Detection in Social Media
%A Alqahtani, Amal
%A Diab, Mona
%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 alqahtani-diab-2026-cross
%X Language-based schizophrenia detection has focused predominantly on English, leaving Arabic underrepresented in mental health NLP. We introduce an Arabic schizophrenia social media dataset (228 users, 228 controls; Cohen’s \ensuremathąppa=0.76) and evaluate cross-lingual and cross-genre transfer across five primary settings and four reversed direction counterparts using XLM-RoBERTa-base, mBERT, and MARBERT. In-domain Arabic supervision yields the strongest performance, with MARBERT reaching 0.7706 macro-F1. In contrast, no primary transfer condition satisfies our criterion for robust transfer (macro-F1 \ensuremath> 0.50 and consistent performance across all three encoders). Reversed direction experiments suggest that genre transfer is directional: social to clinical transfer partially succeeds in the Arabic-only setting, whereas clinical to social transfer collapses. Results from translated clinical data further indicate that translation-based evaluation can introduce artifacts specific to encoder and direction. Overall, the findings support the need for native target language and target genre resources for reliable multilingual mental health evaluation.
%U https://aclanthology.org/2026.multipsyche-1.9/
%P 105-117
Markdown (Informal)
[Cross-Lingual and Cross-Genre Transfer for Arabic Schizophrenia Detection in Social Media](https://aclanthology.org/2026.multipsyche-1.9/) (Alqahtani & Diab, MultiPsyche 2026)
ACL