@inproceedings{cieslak-sredniawa-2026-leakage,
title = "Leakage-Aware User-Level {ADHD} Signal Classification from Social Media: When Graph Aggregation Helps, and When It Does Not",
author = "Cie{\'s}lak, Daniel and
{\'S}redniawa, W{\l}adys{\l}aw",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.47/",
pages = "527--536",
ISBN = "979-8-89176-393-7",
abstract = "User-level ADHD-related text classification from social media is methodologically challenging because predictions must aggregate many short posts, performance can be inflated by direct diagnostic leakage, and screening-adjacent settings require calibrated probabilities rather than discrimination alone. We introduce a leakage-aware evaluation framework organized around two controlled axes: evidence budget, i.e., the number of tweets available per user, and leakage control. Within this setup, we compare document-level transformers, strong non-graph embedding-pooling baselines, and heterogeneous graph models combining semantic tweet embeddings, psycholinguistic features, and temporal structure. The main result is regime-dependent: graph aggregation is most useful when user evidence is scarce, whereas simple embedding pooling becomes highly competitive and often slightly stronger as more evidence becomes available. Overall, the main contribution is a controlled benchmarking framework and a clearer account of when graph-based aggregation is actually beneficial."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cieslak-sredniawa-2026-leakage">
<titleInfo>
<title>Leakage-Aware User-Level ADHD Signal Classification from Social Media: When Graph Aggregation Helps, and When It Does Not</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cieślak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Władysław</namePart>
<namePart type="family">Średniawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>User-level ADHD-related text classification from social media is methodologically challenging because predictions must aggregate many short posts, performance can be inflated by direct diagnostic leakage, and screening-adjacent settings require calibrated probabilities rather than discrimination alone. We introduce a leakage-aware evaluation framework organized around two controlled axes: evidence budget, i.e., the number of tweets available per user, and leakage control. Within this setup, we compare document-level transformers, strong non-graph embedding-pooling baselines, and heterogeneous graph models combining semantic tweet embeddings, psycholinguistic features, and temporal structure. The main result is regime-dependent: graph aggregation is most useful when user evidence is scarce, whereas simple embedding pooling becomes highly competitive and often slightly stronger as more evidence becomes available. Overall, the main contribution is a controlled benchmarking framework and a clearer account of when graph-based aggregation is actually beneficial.</abstract>
<identifier type="citekey">cieslak-sredniawa-2026-leakage</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.47/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>527</start>
<end>536</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leakage-Aware User-Level ADHD Signal Classification from Social Media: When Graph Aggregation Helps, and When It Does Not
%A Cieślak, Daniel
%A Średniawa, Władysław
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F cieslak-sredniawa-2026-leakage
%X User-level ADHD-related text classification from social media is methodologically challenging because predictions must aggregate many short posts, performance can be inflated by direct diagnostic leakage, and screening-adjacent settings require calibrated probabilities rather than discrimination alone. We introduce a leakage-aware evaluation framework organized around two controlled axes: evidence budget, i.e., the number of tweets available per user, and leakage control. Within this setup, we compare document-level transformers, strong non-graph embedding-pooling baselines, and heterogeneous graph models combining semantic tweet embeddings, psycholinguistic features, and temporal structure. The main result is regime-dependent: graph aggregation is most useful when user evidence is scarce, whereas simple embedding pooling becomes highly competitive and often slightly stronger as more evidence becomes available. Overall, the main contribution is a controlled benchmarking framework and a clearer account of when graph-based aggregation is actually beneficial.
%U https://aclanthology.org/2026.acl-srw.47/
%P 527-536
Markdown (Informal)
[Leakage-Aware User-Level ADHD Signal Classification from Social Media: When Graph Aggregation Helps, and When It Does Not](https://aclanthology.org/2026.acl-srw.47/) (Cieślak & Średniawa, ACL 2026)
ACL