@inproceedings{albertelli-2026-modeling,
title = "Modeling Topics as Linguistic Linked Open Data: A First Attempt Using {BERT}opic, Ontolex-Lemon and {F}r{AC}",
author = "Albertelli, Lisa Sophie",
editor = "McCrae, John P. and
Gkirtzou, Katerina and
Khan, Fahad and
Martin Chozas, Patricia and
Carvalho, Sara and
Canning, Erin",
booktitle = "Proceedings of 10th Workshop on Linked Data in Linguistics ({LDL}-2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.ldl-1.1/",
doi = "10.63317/22r5hh55bs8d",
pages = "1--12",
abstract = "Parliamentary discourse constitutes a key domain in which political actors publicly articulate policy positions and priorities through language. This study investigates debates from the Italian Chamber of Deputies (1948{--}2006) to identify and analyse latent semantic themes and their evolution using BERTopic-based dynamic topic modeling. The analysis relies on a subset of the ItaParlCorpus (Cova, 2025), a large-scale, machine-readable corpus enriched with temporal, institutional, and political metadata. Beyond topic extraction,this work addresses a largely unexplored challenge: the formalization of topics derived from unsupervised, embedding-based topic modeling as Linked Data entities, adopting a linguistic perspective. Extracted topics are formalized as semantic entities reusing the OntoLex{--}Lemon model, its FrAC extension and declaring a dedicated ontology to link topics to speeches, speakers, political parties, and temporal information reusing standardized vocabularies and persistent URIs. This integration enables semantic querying through SPARQL, supporting analyses of topic distributions across political actors, parties and illustrating the analytical potential of the proposed approach. Moreover, the study highlights limitations in the formalization of topic modeling outputs, particularly regarding the representation of ambiguous word forms and their alignment with lexical concepts in OntoLex{--}Lemon."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albertelli-2026-modeling">
<titleInfo>
<title>Modeling Topics as Linguistic Linked Open Data: A First Attempt Using BERTopic, Ontolex-Lemon and FrAC</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="given">Sophie</namePart>
<namePart type="family">Albertelli</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 10th Workshop on Linked Data in Linguistics (LDL-2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Martin Chozas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erin</namePart>
<namePart type="family">Canning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parliamentary discourse constitutes a key domain in which political actors publicly articulate policy positions and priorities through language. This study investigates debates from the Italian Chamber of Deputies (1948–2006) to identify and analyse latent semantic themes and their evolution using BERTopic-based dynamic topic modeling. The analysis relies on a subset of the ItaParlCorpus (Cova, 2025), a large-scale, machine-readable corpus enriched with temporal, institutional, and political metadata. Beyond topic extraction,this work addresses a largely unexplored challenge: the formalization of topics derived from unsupervised, embedding-based topic modeling as Linked Data entities, adopting a linguistic perspective. Extracted topics are formalized as semantic entities reusing the OntoLex–Lemon model, its FrAC extension and declaring a dedicated ontology to link topics to speeches, speakers, political parties, and temporal information reusing standardized vocabularies and persistent URIs. This integration enables semantic querying through SPARQL, supporting analyses of topic distributions across political actors, parties and illustrating the analytical potential of the proposed approach. Moreover, the study highlights limitations in the formalization of topic modeling outputs, particularly regarding the representation of ambiguous word forms and their alignment with lexical concepts in OntoLex–Lemon.</abstract>
<identifier type="citekey">albertelli-2026-modeling</identifier>
<identifier type="doi">10.63317/22r5hh55bs8d</identifier>
<location>
<url>https://aclanthology.org/2026.ldl-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Topics as Linguistic Linked Open Data: A First Attempt Using BERTopic, Ontolex-Lemon and FrAC
%A Albertelli, Lisa Sophie
%Y McCrae, John P.
%Y Gkirtzou, Katerina
%Y Khan, Fahad
%Y Martin Chozas, Patricia
%Y Carvalho, Sara
%Y Canning, Erin
%S Proceedings of 10th Workshop on Linked Data in Linguistics (LDL-2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F albertelli-2026-modeling
%X Parliamentary discourse constitutes a key domain in which political actors publicly articulate policy positions and priorities through language. This study investigates debates from the Italian Chamber of Deputies (1948–2006) to identify and analyse latent semantic themes and their evolution using BERTopic-based dynamic topic modeling. The analysis relies on a subset of the ItaParlCorpus (Cova, 2025), a large-scale, machine-readable corpus enriched with temporal, institutional, and political metadata. Beyond topic extraction,this work addresses a largely unexplored challenge: the formalization of topics derived from unsupervised, embedding-based topic modeling as Linked Data entities, adopting a linguistic perspective. Extracted topics are formalized as semantic entities reusing the OntoLex–Lemon model, its FrAC extension and declaring a dedicated ontology to link topics to speeches, speakers, political parties, and temporal information reusing standardized vocabularies and persistent URIs. This integration enables semantic querying through SPARQL, supporting analyses of topic distributions across political actors, parties and illustrating the analytical potential of the proposed approach. Moreover, the study highlights limitations in the formalization of topic modeling outputs, particularly regarding the representation of ambiguous word forms and their alignment with lexical concepts in OntoLex–Lemon.
%R 10.63317/22r5hh55bs8d
%U https://aclanthology.org/2026.ldl-1.1/
%U https://doi.org/10.63317/22r5hh55bs8d
%P 1-12
Markdown (Informal)
[Modeling Topics as Linguistic Linked Open Data: A First Attempt Using BERTopic, Ontolex-Lemon and FrAC](https://aclanthology.org/2026.ldl-1.1/) (Albertelli, LDL 2026)
ACL