@inproceedings{lima-etal-2026-balancing,
title = "Balancing Coherence and Granularity in Legal Topic Modeling: A {BERT}opic-based Study on {P}ortuguese Appellate Court Decisions",
author = "Lima, Marjory S. S. and
Ahad, Felipe R. and
Silva, Vih A. S. and
Ventura, Thiago M. and
Figueiredo, Josiel M. and
de Oliveira, Allan G.",
editor = "Barbosa, Bryan Khelven da Silva and
Paes, Aline and
Felippo, Ariani Di",
booktitle = "Proceedings of the 17th {B}razilian Symposium in Information and Human Language Technology",
month = oct,
year = "2026",
address = "Cuiab{\'a}, Mato Grosso, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.stil-1.19/",
doi = "10.5753/stil.2026.26502",
pages = "218--230",
abstract = "The growing backlog of the Brazilian Judiciary demands scalable semantic organization beyond keyword-based retrieval. This study investigates the trade-off between topic coherence and thematic granularity in neural topic modeling for legal texts. We cluster 1,831 Brazilian labor summaries using BERTopic with LegalBERT-pt embeddings and evaluate the impact of the min{\_}topic{\_}size parameter on coherence (Cv), granularity, and diversity. We propose a balanced evaluation score integrating coherence and granularity. Results show higher coherence (Cv {\ensuremath{\approx}} 0.78) than Latent Dirichlet Allocation (Cv {\ensuremath{\approx}} 0.49), while enabling controlled topic resolution. These findings provide a practical criterion for tuning topic models in large-scale legal systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lima-etal-2026-balancing">
<titleInfo>
<title>Balancing Coherence and Granularity in Legal Topic Modeling: A BERTopic-based Study on Portuguese Appellate Court Decisions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marjory</namePart>
<namePart type="given">S</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Lima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Ahad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vih</namePart>
<namePart type="given">A</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ventura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josiel</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Figueiredo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Allan</namePart>
<namePart type="given">G</namePart>
<namePart type="family">de Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">Khelven</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Barbosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Paes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariani</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Felippo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Cuiabá, Mato Grosso, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The growing backlog of the Brazilian Judiciary demands scalable semantic organization beyond keyword-based retrieval. This study investigates the trade-off between topic coherence and thematic granularity in neural topic modeling for legal texts. We cluster 1,831 Brazilian labor summaries using BERTopic with LegalBERT-pt embeddings and evaluate the impact of the min_topic_size parameter on coherence (Cv), granularity, and diversity. We propose a balanced evaluation score integrating coherence and granularity. Results show higher coherence (Cv \ensuremath\approx 0.78) than Latent Dirichlet Allocation (Cv \ensuremath\approx 0.49), while enabling controlled topic resolution. These findings provide a practical criterion for tuning topic models in large-scale legal systems.</abstract>
<identifier type="citekey">lima-etal-2026-balancing</identifier>
<identifier type="doi">10.5753/stil.2026.26502</identifier>
<location>
<url>https://aclanthology.org/2026.stil-1.19/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>218</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Balancing Coherence and Granularity in Legal Topic Modeling: A BERTopic-based Study on Portuguese Appellate Court Decisions
%A Lima, Marjory S. S.
%A Ahad, Felipe R.
%A Silva, Vih A. S.
%A Ventura, Thiago M.
%A Figueiredo, Josiel M.
%A de Oliveira, Allan G.
%Y Barbosa, Bryan Khelven da Silva
%Y Paes, Aline
%Y Felippo, Ariani Di
%S Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
%D 2026
%8 October
%I Association for Computational Linguistics
%C Cuiabá, Mato Grosso, Brazil
%F lima-etal-2026-balancing
%X The growing backlog of the Brazilian Judiciary demands scalable semantic organization beyond keyword-based retrieval. This study investigates the trade-off between topic coherence and thematic granularity in neural topic modeling for legal texts. We cluster 1,831 Brazilian labor summaries using BERTopic with LegalBERT-pt embeddings and evaluate the impact of the min_topic_size parameter on coherence (Cv), granularity, and diversity. We propose a balanced evaluation score integrating coherence and granularity. Results show higher coherence (Cv \ensuremath\approx 0.78) than Latent Dirichlet Allocation (Cv \ensuremath\approx 0.49), while enabling controlled topic resolution. These findings provide a practical criterion for tuning topic models in large-scale legal systems.
%R 10.5753/stil.2026.26502
%U https://aclanthology.org/2026.stil-1.19/
%U https://doi.org/10.5753/stil.2026.26502
%P 218-230
Markdown (Informal)
[Balancing Coherence and Granularity in Legal Topic Modeling: A BERTopic-based Study on Portuguese Appellate Court Decisions](https://aclanthology.org/2026.stil-1.19/) (Lima et al., STIL 2026)
ACL