@inproceedings{amini-kosseim-2025-posts,
title = "From Posts to Predictions: A User-Aware Framework for Faithful and Transparent Detection of Mental Health Risks on Social Media",
author = "Amini, Hessam and
Kosseim, Leila",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.9/",
pages = "75--84",
abstract = "We propose a user-aware attention-based framework for early detection of mental health risks from social media posts. Our model combines DisorBERT, a mental health{--}adapted transformer encoder, with a user-level attention mechanism that produces transparent post-level explanations. To assess whether these explanations are faithful, i.e., aligned with the model{'}s true decision process, we apply adversarial training and quantify attention faithfulness using the AtteFa metric. Experiments on four eRisk tasks (depression, anorexia, self-harm, and pathological gambling) show that our model achieves competitive latency-weighted F1 scores while relying on a sparse subset of posts per user. We also evaluate attention robustness and conduct ablations, confirming the model{'}s reliance on high-weighted posts. Our work extends prior explainability studies by integrating faithfulness assessment in a real-world high-stakes application. We argue that systems combining predictive accuracy with faithful and transparent explanations offer a promising path toward safe and trustworthy AI for mental health support."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amini-kosseim-2025-posts">
<titleInfo>
<title>From Posts to Predictions: A User-Aware Framework for Faithful and Transparent Detection of Mental Health Risks on Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hessam</namePart>
<namePart type="family">Amini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leila</namePart>
<namePart type="family">Kosseim</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 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</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>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a user-aware attention-based framework for early detection of mental health risks from social media posts. Our model combines DisorBERT, a mental health–adapted transformer encoder, with a user-level attention mechanism that produces transparent post-level explanations. To assess whether these explanations are faithful, i.e., aligned with the model’s true decision process, we apply adversarial training and quantify attention faithfulness using the AtteFa metric. Experiments on four eRisk tasks (depression, anorexia, self-harm, and pathological gambling) show that our model achieves competitive latency-weighted F1 scores while relying on a sparse subset of posts per user. We also evaluate attention robustness and conduct ablations, confirming the model’s reliance on high-weighted posts. Our work extends prior explainability studies by integrating faithfulness assessment in a real-world high-stakes application. We argue that systems combining predictive accuracy with faithful and transparent explanations offer a promising path toward safe and trustworthy AI for mental health support.</abstract>
<identifier type="citekey">amini-kosseim-2025-posts</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.9/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>75</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Posts to Predictions: A User-Aware Framework for Faithful and Transparent Detection of Mental Health Risks on Social Media
%A Amini, Hessam
%A Kosseim, Leila
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F amini-kosseim-2025-posts
%X We propose a user-aware attention-based framework for early detection of mental health risks from social media posts. Our model combines DisorBERT, a mental health–adapted transformer encoder, with a user-level attention mechanism that produces transparent post-level explanations. To assess whether these explanations are faithful, i.e., aligned with the model’s true decision process, we apply adversarial training and quantify attention faithfulness using the AtteFa metric. Experiments on four eRisk tasks (depression, anorexia, self-harm, and pathological gambling) show that our model achieves competitive latency-weighted F1 scores while relying on a sparse subset of posts per user. We also evaluate attention robustness and conduct ablations, confirming the model’s reliance on high-weighted posts. Our work extends prior explainability studies by integrating faithfulness assessment in a real-world high-stakes application. We argue that systems combining predictive accuracy with faithful and transparent explanations offer a promising path toward safe and trustworthy AI for mental health support.
%U https://aclanthology.org/2025.ranlp-1.9/
%P 75-84
Markdown (Informal)
[From Posts to Predictions: A User-Aware Framework for Faithful and Transparent Detection of Mental Health Risks on Social Media](https://aclanthology.org/2025.ranlp-1.9/) (Amini & Kosseim, RANLP 2025)
ACL