@inproceedings{plhak-etal-2026-detecting,
title = "Detecting Risky Behavior Related to Alcohol and Drug Use within Adolescents' Private Messenger Conversations",
author = "Plh{\'a}k, Jarom{\'i}r and
Lebed{\'i}kov{\'a}, Michaela and
Sotolar, Ondrej and
Smahel, David",
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-1.201/",
doi = "10.63317/2rjd9g5nbkxv",
pages = "2567--2580",
abstract = "Alcohol and drug use negatively impact adolescents' health, making early detection and prevention essential. One promising approach involves analyzing adolescents' online conversations for signs of substance use. However, current machine learning models for online detection often rely on public data sources that fail to capture the private experiences of adolescents. In this study, we developed a BERT-based machine learning model to automatically identify discussions about alcohol and drug use with high accuracy, leveraging private messenger conversations from adolescents. Our novel dataset comprises 272,465 annotated utterances from a corpus of 1,260,492 utterances in 2,807 chats authored by 2,165 individuals, primarily in Czech. Our best BERT-based machine learning model achieved a solid $F_1$ score of 0.817, demonstrating the feasibility of addressing this social science task even in low-resource languages like Czech. Additionally, we verified that state-of-the-art generative open-source large language models are equally effective for this task and can be successfully adapted for other languages, including English. We also analyzed misclassified utterances to identify problematic patterns and improve model performance. The resulting models have significant practical implications for parental mediation software and parental control applications. By automating substance use detection and enabling appropriate real-time interventions, these tools can contribute to safeguarding adolescents' health."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plhak-etal-2026-detecting">
<titleInfo>
<title>Detecting Risky Behavior Related to Alcohol and Drug Use within Adolescents’ Private Messenger Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaromír</namePart>
<namePart type="family">Plhák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michaela</namePart>
<namePart type="family">Lebedíková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Sotolar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Smahel</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>Alcohol and drug use negatively impact adolescents’ health, making early detection and prevention essential. One promising approach involves analyzing adolescents’ online conversations for signs of substance use. However, current machine learning models for online detection often rely on public data sources that fail to capture the private experiences of adolescents. In this study, we developed a BERT-based machine learning model to automatically identify discussions about alcohol and drug use with high accuracy, leveraging private messenger conversations from adolescents. Our novel dataset comprises 272,465 annotated utterances from a corpus of 1,260,492 utterances in 2,807 chats authored by 2,165 individuals, primarily in Czech. Our best BERT-based machine learning model achieved a solid F₁ score of 0.817, demonstrating the feasibility of addressing this social science task even in low-resource languages like Czech. Additionally, we verified that state-of-the-art generative open-source large language models are equally effective for this task and can be successfully adapted for other languages, including English. We also analyzed misclassified utterances to identify problematic patterns and improve model performance. The resulting models have significant practical implications for parental mediation software and parental control applications. By automating substance use detection and enabling appropriate real-time interventions, these tools can contribute to safeguarding adolescents’ health.</abstract>
<identifier type="citekey">plhak-etal-2026-detecting</identifier>
<identifier type="doi">10.63317/2rjd9g5nbkxv</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.201/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2567</start>
<end>2580</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Risky Behavior Related to Alcohol and Drug Use within Adolescents’ Private Messenger Conversations
%A Plhák, Jaromír
%A Lebedíková, Michaela
%A Sotolar, Ondrej
%A Smahel, David
%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 plhak-etal-2026-detecting
%X Alcohol and drug use negatively impact adolescents’ health, making early detection and prevention essential. One promising approach involves analyzing adolescents’ online conversations for signs of substance use. However, current machine learning models for online detection often rely on public data sources that fail to capture the private experiences of adolescents. In this study, we developed a BERT-based machine learning model to automatically identify discussions about alcohol and drug use with high accuracy, leveraging private messenger conversations from adolescents. Our novel dataset comprises 272,465 annotated utterances from a corpus of 1,260,492 utterances in 2,807 chats authored by 2,165 individuals, primarily in Czech. Our best BERT-based machine learning model achieved a solid F₁ score of 0.817, demonstrating the feasibility of addressing this social science task even in low-resource languages like Czech. Additionally, we verified that state-of-the-art generative open-source large language models are equally effective for this task and can be successfully adapted for other languages, including English. We also analyzed misclassified utterances to identify problematic patterns and improve model performance. The resulting models have significant practical implications for parental mediation software and parental control applications. By automating substance use detection and enabling appropriate real-time interventions, these tools can contribute to safeguarding adolescents’ health.
%R 10.63317/2rjd9g5nbkxv
%U https://aclanthology.org/2026.lrec-1.201/
%U https://doi.org/10.63317/2rjd9g5nbkxv
%P 2567-2580
Markdown (Informal)
[Detecting Risky Behavior Related to Alcohol and Drug Use within Adolescents’ Private Messenger Conversations](https://aclanthology.org/2026.lrec-1.201/) (Plhák et al., LREC 2026)
ACL