Topic Modeling in Brazilian Portuguese Documents on Antimicrobial Resistance

2026-04-12 · Source: Paper Index on ACL Anthology · Field: Health & Wellbeing — Public Health & Epidemiology, Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Advanced, quick

Summary

A study analyzed Brazilian Portuguese documents on antimicrobial resistance from diverse sources to support epidemiological surveillance and public policy. Three datasets were utilized: 64,225 tweets collected between 2008 and 2025, 4,363 news articles from G1, and 1,515 official government publications from .gov.br. This allowed for a comparative analysis of informal discourse from social media against institutional and journalistic discourse. The research applied and compared Short Text Topic Modeling (STTM) techniques, specifically GSDMM and BERTopic, to identify discursive trends, semantic patterns, and emerging topics related to antimicrobial resistance. The work highlights the potential of Natural Language Processing (NLP) and AI methods for integrated public health data analysis across informal and formal environments.

Key takeaway

For public health analysts monitoring societal discourse on critical issues like antimicrobial resistance, integrating informal social media data with formal news and government publications provides a comprehensive view. You should consider employing Short Text Topic Modeling techniques such as GSDMM or BERTopic to effectively extract trends and semantic patterns from these varied text sources, informing epidemiological surveillance and policy decisions.

Key insights

Topic modeling on diverse text sources can reveal public discourse patterns on critical health issues.

Principles

• Diverse data sources enrich discourse analysis.
• STTM techniques suit varied text lengths.

Method

The study involved collecting tweets, news articles, and government publications, then applying and comparing GSDMM and BERTopic for topic modeling to identify semantic patterns.

In practice

• Use GSDMM for short text topic modeling.
• Apply BERTopic for robust topic extraction.

Topics

• Antimicrobial Resistance
• Topic Modeling
• Brazilian Portuguese
• Short Text Topic Modeling
• GSDMM

Best for: NLP Engineer, AI Scientist, Research Scientist, Policy Maker

Related on AIssential

• Towards a Universal Dependencies Corpus for Portuguese Epidemiological Reports — Document extraction and representation significantly impact parsing epidemiological texts more than parser selection.
• Experimental Evaluation of Topic Modeling Methods for Categorizing Irregularities in Health-related news — LSA topic modeling effectively categorizes health news irregularities, enhancing public health audit efficiency.
• Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach — Computational methods can reveal hidden patterns in parliamentary discourse beyond voting records.
• Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning? — LLMs offer a viable few-shot alternative for biomedical relation extraction, outperforming prior few-shot methods, especially for rare relations.
• From 50K to 8.2 Million in 24 Hours: Vozinha's Algorithmic Consecration and the Multilingual Making of World Cup Visibility — Algorithmic visibility for public figures is shaped by distinct cross-lingual narrative frames and platform metrics.
• EDEN: A Large-Scale Corpus of Clinical Notes for Italian — EDEN provides the largest Italian clinical note corpus and a CRF-filling benchmark for LLM-based information extraction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.