@inproceedings{nguyen-2026-ecological,
title = "Ecological Discourse Modeling in a Low-Resource Setting: A Longitudinal {V}ietnamese Climate Corpus with Comparative Topic Modeling",
author = "Nguyen, Huyen Phuong",
editor = "Grasso, Francesca and
Basile, Valerio and
Bosco, Cristina and
Ibrohim, Muhammad Okky and
Skeppstedt, Maria and
Stede, Manfred",
booktitle = "Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2026.nlp4ecology-1.7/",
doi = "10.63317/4n8q3zryqvju",
pages = "69--78",
abstract = "Climate change discourse has expanded substantially in recent decades, yet computational analyses remain concentrated on high-resource languages. In this paper, we construct a longitudinal Vietnamese climate news corpus and examine thematic structure and temporal evolution in a lower-resource setting. The corpus comprises 10,401 articles published between 2004 and 2026 and is systematically preprocessed using linguistically informed word segmentation. To ensure domestic relevance, we apply transformer-based Named Entity Recognition and construct a geographically grounded subset of 4,501 Vietnam-focused documents. We analyze this dataset using both Latent Dirichlet Allocation and BERTopic. Results reveal stable thematic dimensions alongside longitudinal shifts from event-driven pollution reporting toward governance- and energy-centered narratives. Embedding-based modeling achieves higher semantic coherence while maintaining comparable topic diversity. The main contribution of this work is thus the compilation of a structured Vietnamese climate corpus and a systematic analysis of discourse evolution in an underrepresented language context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-2026-ecological">
<titleInfo>
<title>Ecological Discourse Modeling in a Low-Resource Setting: A Longitudinal Vietnamese Climate Corpus with Comparative Topic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huyen</namePart>
<namePart type="given">Phuong</namePart>
<namePart type="family">Nguyen</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 2nd Workshop on Ecology, Environment, and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Grasso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Okky</namePart>
<namePart type="family">Ibrohim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Skeppstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Climate change discourse has expanded substantially in recent decades, yet computational analyses remain concentrated on high-resource languages. In this paper, we construct a longitudinal Vietnamese climate news corpus and examine thematic structure and temporal evolution in a lower-resource setting. The corpus comprises 10,401 articles published between 2004 and 2026 and is systematically preprocessed using linguistically informed word segmentation. To ensure domestic relevance, we apply transformer-based Named Entity Recognition and construct a geographically grounded subset of 4,501 Vietnam-focused documents. We analyze this dataset using both Latent Dirichlet Allocation and BERTopic. Results reveal stable thematic dimensions alongside longitudinal shifts from event-driven pollution reporting toward governance- and energy-centered narratives. Embedding-based modeling achieves higher semantic coherence while maintaining comparable topic diversity. The main contribution of this work is thus the compilation of a structured Vietnamese climate corpus and a systematic analysis of discourse evolution in an underrepresented language context.</abstract>
<identifier type="citekey">nguyen-2026-ecological</identifier>
<identifier type="doi">10.63317/4n8q3zryqvju</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4ecology-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>69</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ecological Discourse Modeling in a Low-Resource Setting: A Longitudinal Vietnamese Climate Corpus with Comparative Topic Modeling
%A Nguyen, Huyen Phuong
%Y Grasso, Francesca
%Y Basile, Valerio
%Y Bosco, Cristina
%Y Ibrohim, Muhammad Okky
%Y Skeppstedt, Maria
%Y Stede, Manfred
%S Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing
%D 2026
%8 May
%I European Language Resources Association
%C Palma de Mallorca, Spain
%F nguyen-2026-ecological
%X Climate change discourse has expanded substantially in recent decades, yet computational analyses remain concentrated on high-resource languages. In this paper, we construct a longitudinal Vietnamese climate news corpus and examine thematic structure and temporal evolution in a lower-resource setting. The corpus comprises 10,401 articles published between 2004 and 2026 and is systematically preprocessed using linguistically informed word segmentation. To ensure domestic relevance, we apply transformer-based Named Entity Recognition and construct a geographically grounded subset of 4,501 Vietnam-focused documents. We analyze this dataset using both Latent Dirichlet Allocation and BERTopic. Results reveal stable thematic dimensions alongside longitudinal shifts from event-driven pollution reporting toward governance- and energy-centered narratives. Embedding-based modeling achieves higher semantic coherence while maintaining comparable topic diversity. The main contribution of this work is thus the compilation of a structured Vietnamese climate corpus and a systematic analysis of discourse evolution in an underrepresented language context.
%R 10.63317/4n8q3zryqvju
%U https://aclanthology.org/2026.nlp4ecology-1.7/
%U https://doi.org/10.63317/4n8q3zryqvju
%P 69-78
Markdown (Informal)
[Ecological Discourse Modeling in a Low-Resource Setting: A Longitudinal Vietnamese Climate Corpus with Comparative Topic Modeling](https://aclanthology.org/2026.nlp4ecology-1.7/) (Nguyen, NLP4Ecology 2026)
ACL