@inproceedings{sarif-etal-2025-identifying,
title = "Identifying Severity of Depression in Forum Posts using Zero-Shot Classifier and {D}istil{BERT} Model",
author = "Sarif, Zafar and
Das, Sannidhya and
Das, Dr. Abhishek and
Parvej, Md Fahin and
Das, Dipankar",
editor = "Arachchige, Isuri Nanomi and
Frontini, Francesca and
Mitkov, Ruslan and
Rayson, Paul",
booktitle = "Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.lm4dh-1.12/",
pages = "126--132",
abstract = "This paper presents our approach to the RANLP 2025 Shared Task on ``Identification of the Severity of Depression in Forum Posts.'' The objective of the task is to classify user-generated posts into one of four severity levels of depression: subthreshold, mild, moderate, or severe. A key challenge in the task was the absence of annotated training data. To address this, we employed a two-stage pipeline: first, we used zero-shot classification with facebook/bart-large-mnli to generate pseudo-labels for the unlabeled training set. Next, we fine-tuned a DistilBERT model on the pseudo-labeled data for multi-class classification. Our system achieved an internal accuracy of 0.92 on the pseudo-labeled test set and an accuracy of 0.289 on the official blind evaluation set. These results demonstrate the feasibility of leveraging zero-shot learning and weak supervision for mental health classification tasks, even in the absence of gold-standard annotations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarif-etal-2025-identifying">
<titleInfo>
<title>Identifying Severity of Depression in Forum Posts using Zero-Shot Classifier and DistilBERT Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zafar</namePart>
<namePart type="family">Sarif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sannidhya</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dr.</namePart>
<namePart type="given">Abhishek</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Fahin</namePart>
<namePart type="family">Parvej</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isuri</namePart>
<namePart type="given">Nanomi</namePart>
<namePart type="family">Arachchige</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Frontini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our approach to the RANLP 2025 Shared Task on “Identification of the Severity of Depression in Forum Posts.” The objective of the task is to classify user-generated posts into one of four severity levels of depression: subthreshold, mild, moderate, or severe. A key challenge in the task was the absence of annotated training data. To address this, we employed a two-stage pipeline: first, we used zero-shot classification with facebook/bart-large-mnli to generate pseudo-labels for the unlabeled training set. Next, we fine-tuned a DistilBERT model on the pseudo-labeled data for multi-class classification. Our system achieved an internal accuracy of 0.92 on the pseudo-labeled test set and an accuracy of 0.289 on the official blind evaluation set. These results demonstrate the feasibility of leveraging zero-shot learning and weak supervision for mental health classification tasks, even in the absence of gold-standard annotations.</abstract>
<identifier type="citekey">sarif-etal-2025-identifying</identifier>
<location>
<url>https://aclanthology.org/2025.lm4dh-1.12/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>126</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Severity of Depression in Forum Posts using Zero-Shot Classifier and DistilBERT Model
%A Sarif, Zafar
%A Das, Sannidhya
%A Das, Dr. Abhishek
%A Parvej, Md Fahin
%A Das, Dipankar
%Y Arachchige, Isuri Nanomi
%Y Frontini, Francesca
%Y Mitkov, Ruslan
%Y Rayson, Paul
%S Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F sarif-etal-2025-identifying
%X This paper presents our approach to the RANLP 2025 Shared Task on “Identification of the Severity of Depression in Forum Posts.” The objective of the task is to classify user-generated posts into one of four severity levels of depression: subthreshold, mild, moderate, or severe. A key challenge in the task was the absence of annotated training data. To address this, we employed a two-stage pipeline: first, we used zero-shot classification with facebook/bart-large-mnli to generate pseudo-labels for the unlabeled training set. Next, we fine-tuned a DistilBERT model on the pseudo-labeled data for multi-class classification. Our system achieved an internal accuracy of 0.92 on the pseudo-labeled test set and an accuracy of 0.289 on the official blind evaluation set. These results demonstrate the feasibility of leveraging zero-shot learning and weak supervision for mental health classification tasks, even in the absence of gold-standard annotations.
%U https://aclanthology.org/2025.lm4dh-1.12/
%P 126-132
Markdown (Informal)
[Identifying Severity of Depression in Forum Posts using Zero-Shot Classifier and DistilBERT Model](https://aclanthology.org/2025.lm4dh-1.12/) (Sarif et al., LM4DH 2025)
ACL
