@inproceedings{ciobotaru-etal-2026-psihoro,
title = "{P}siho{R}o: Depression and Anxiety {R}omanian Text Corpus",
author = "Ciobotaru, Alexandra and
Bucur, Ana-Maria and
Dinu, Liviu P.",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.271/",
doi = "10.63317/2958cfzsyg7a",
pages = "3423--3433",
abstract = "Psychological corpora in NLP are collections of texts used to analyze human psychology, emotions, and mental health. These texts allow researchers to study psychological constructs, identify patterns related to mental health problems and analyze emotional language. However, collecting accurate mental health data from social media can be challenging due to the assumptions made by data collectors. A more effective approach involves gathering data through open-ended questions and then assessing participants' mental health status using self-report screening surveys. This method was successfully employed for English, a language with a lot of psychological NLP resources. However, the same cannot be stated for Romanian, which currently has no open-source mental health corpus. To address this gap, we have collected the first open-source corpus focused on depression and anxiety in Romanian, by utilizing a form with 6 open-ended questions along with the standardized PHQ-9 and GAD-7 screening questionnaires. Although the PsihoRo corpus contains texts from only 205 respondents, it represents an important first step toward understanding and analyzing mental health issues within the Romanian population. We employ statistical analysis, text analysis using Romanian LIWC, emotion detection, and topic modeling to identify the most important features of this newly introduced resource for the NLP community. The data is publicly available at \url{https://huggingface.co/datasets/Alegzandra/PsihoRo}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ciobotaru-etal-2026-psihoro">
<titleInfo>
<title>PsihoRo: Depression and Anxiety Romanian Text Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Ciobotaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana-Maria</namePart>
<namePart type="family">Bucur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liviu</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dinu</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Psychological corpora in NLP are collections of texts used to analyze human psychology, emotions, and mental health. These texts allow researchers to study psychological constructs, identify patterns related to mental health problems and analyze emotional language. However, collecting accurate mental health data from social media can be challenging due to the assumptions made by data collectors. A more effective approach involves gathering data through open-ended questions and then assessing participants’ mental health status using self-report screening surveys. This method was successfully employed for English, a language with a lot of psychological NLP resources. However, the same cannot be stated for Romanian, which currently has no open-source mental health corpus. To address this gap, we have collected the first open-source corpus focused on depression and anxiety in Romanian, by utilizing a form with 6 open-ended questions along with the standardized PHQ-9 and GAD-7 screening questionnaires. Although the PsihoRo corpus contains texts from only 205 respondents, it represents an important first step toward understanding and analyzing mental health issues within the Romanian population. We employ statistical analysis, text analysis using Romanian LIWC, emotion detection, and topic modeling to identify the most important features of this newly introduced resource for the NLP community. The data is publicly available at https://huggingface.co/datasets/Alegzandra/PsihoRo.</abstract>
<identifier type="citekey">ciobotaru-etal-2026-psihoro</identifier>
<identifier type="doi">10.63317/2958cfzsyg7a</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.271/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3423</start>
<end>3433</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PsihoRo: Depression and Anxiety Romanian Text Corpus
%A Ciobotaru, Alexandra
%A Bucur, Ana-Maria
%A Dinu, Liviu P.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ciobotaru-etal-2026-psihoro
%X Psychological corpora in NLP are collections of texts used to analyze human psychology, emotions, and mental health. These texts allow researchers to study psychological constructs, identify patterns related to mental health problems and analyze emotional language. However, collecting accurate mental health data from social media can be challenging due to the assumptions made by data collectors. A more effective approach involves gathering data through open-ended questions and then assessing participants’ mental health status using self-report screening surveys. This method was successfully employed for English, a language with a lot of psychological NLP resources. However, the same cannot be stated for Romanian, which currently has no open-source mental health corpus. To address this gap, we have collected the first open-source corpus focused on depression and anxiety in Romanian, by utilizing a form with 6 open-ended questions along with the standardized PHQ-9 and GAD-7 screening questionnaires. Although the PsihoRo corpus contains texts from only 205 respondents, it represents an important first step toward understanding and analyzing mental health issues within the Romanian population. We employ statistical analysis, text analysis using Romanian LIWC, emotion detection, and topic modeling to identify the most important features of this newly introduced resource for the NLP community. The data is publicly available at https://huggingface.co/datasets/Alegzandra/PsihoRo.
%R 10.63317/2958cfzsyg7a
%U https://aclanthology.org/2026.lrec-1.271/
%U https://doi.org/10.63317/2958cfzsyg7a
%P 3423-3433
Markdown (Informal)
[PsihoRo: Depression and Anxiety Romanian Text Corpus](https://aclanthology.org/2026.lrec-1.271/) (Ciobotaru et al., LREC 2026)
ACL
- Alexandra Ciobotaru, Ana-Maria Bucur, and Liviu P. Dinu. 2026. PsihoRo: Depression and Anxiety Romanian Text Corpus. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3423–3433, Palma de Mallorca, Spain. ELRA Language Resource Association.