Comparative Evaluation and Optimization of Machine Learning Models for Polarity Classification in Portuguese Movie Reviews
DOI:
https://doi.org/10.5281/zenodo.20297694Keywords:
Natural Language Processin, Sentiment Analysis, Machine Learning, Text Classification.Abstract
This study details the evaluation of Machine Learning models for polarity classification (positive, negative, and neutral) in Portuguese language sentences. The experimental workflow involved two main analyses. First, a dataset was labeled and vectorized (TF-IDF with 2000 features) to train a baseline Multinomial Naive Bayes model (80/20 split), which achieved 38% accuracy. In a second analysis, the same dataset was vectorized (TF-IDF with 5000 features) and evaluated (75/25 split) with four baseline models: Linear SVM, KNN (k=5), Naive Bayes, and Logistic Regression. The SVM (LinearSVC) and LogisticRegression models achieved the best results (accuracy: 0.42), while KNN showed the worst performance (accuracy: 0.26). Hyperparameter optimization using GridSearchCV was applied to the top-performing models (SVM and Logistic Regression) but resulted in no performance improvement. The final analysis indicates that all tested models showed limited overall performance, with significant difficulty in correctly distinguishing the three polarity classes.
Downloads
References
ALVES, Pedro. Métricas de Avaliação de Modelos em Machine Learning – Parte 2. PA Analytics, [S.l.], 29 maio 2020. Disponível em: https://paanalytics.net/blog/metricas-de-avaliacao-de-modelos-em-machine-learning-2/ . Acesso em: 12 nov. 2025.
AMAZON WEB SERVICES. O que é processamento de linguagem natural (PLN)? [S.l.], [s.d.]. Disponível em: https://aws.amazon.com/pt/what-is/nlp/ . Acesso em: 30 out. 2025.
BANSAL, Shivam. Tune Hyperparameters with GridSearchCV. Analytics Vidhya, [S.l.], 15 jun. 2021. Disponível em: https://www.analyticsvidhya.com/blog/2021/06/tune-hyperparameters-with-gridsearchcv/ . Acesso em: 17 nov. 2025.
CODEFINITY. Noções Básicas de PLN | Análise de Sentimento. [S.l.], [s.d.]. Disponível em: https://codefinity.com/pt/courses/v2/74c4663f-0c4d-4527-a77c-8cb957605e29/e433d219-0703-431c-8396-6f494dfd4665/6d289933-ede7-4e91-8f0b-beb80da42a58 . Acesso em: 22 out. 2025.
ELASTIC. O que é a análise de sentimentos? Um guia técnico abrangente. [S.l.], [s.d.]. Disponível em: https://www.elastic.co/pt/what-is/sentiment-analysis . Acesso em: 03 nov. 2025.
HOLCOMBE, Jeremy. O que é Web Scraping? Kinsta, 01 out. 2025. Disponível em: https://kinsta.com/pt/blog/o-que-e-web-scraping/ . Acesso em: 17 nov. 2025.
LEARN DATA SCI. TF-IDF (Term Frequency-Inverse Document Frequency). [S.l.], [s.d.]. Disponível em: https://www.learndatasci.com/glossary/tf-idf-term-frequency-inverse-document-frequency/ . Acesso em: 17 nov. 2025.
STRYKER, Cole; HOLDSWORTH, Jim. O que é processamento de linguagem natural (PLN)? IBM Think, [S.l.], [s.d.]. Disponível em: https://www.ibm.com/br-pt/think/topics/natural-language-processing . Acesso em: 16 nov. 2025.
TYAGI, Harshit. How Machine Learning Uses Linear Algebra to Solve Data Problems. freeCodeCamp.org, [S.l.], 1 set. 2021. Disponível em: https://www.freecodecamp.org/news/how-machine-learning-leverages-linear-algebra-to-optimize-model-trainingwhy-you-should-learn-the-fundamentals-of-linear-algebra/ . Acesso em: 17 nov. 2025.
YOKOYAMA, Naoki. Modelos de Machine Learning. Medium, 30 out. 2020. Disponível em: https://naokiyokoyama.medium.com/modelos-de-machine-learning-bcb3f8ed1513 . Acesso em: 08 nov. 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Robert Richard Neves C. dos Santos, Allan Messias Pinto , Carlos Eduardo França Amador , José Augusto Theodósio Pazetti , Vagner dos Santos Macedo
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright Policy
By submitting a manuscript for publication in the journal Advances in Global Innovation & Technology (@_GIT), authors agree, in advance and unrestrictedly, to the following terms:
- The authors retain the copyright and grant to the Journal Advances in Global Innovation & Technology (@_GIT) the right of first publication of the manuscript, without any financial burden, and waive any other remuneration for its publication in the Journal of Advances in Global Innovation & Technology (@_GIT).
- Upon submission to the Journal of Advances in Global Innovation & Technology (@_GIT), the manuscript is automatically licensed under the Creative Commons Attribution License, which allows the sharing of the work with acknowledgment of authorship and initial publication in the Journal Advances in Global Innovation & Technology (@_GIT).
- Authors are authorized to enter into additional contracts separately, for non-exclusive distribution of the version of the work published in the Journal Advances in Global Innovation & Technology (@_GIT) (publish in repositories or as a book chapter), with acknowledgment of the initial publication in the Journal Advances in Global Innovation & Technology (@_GIT), provided that such agreement does not imply an endorsement of the content of the manuscript or the new vehicle by the Journal of Advances in Global Innovation & Technology (@_GIT).
- Authors are allowed and encouraged to publish and distribute their work online, in institutional repositories, for example after the editorial process is completed.
- The authors warrant that they have obtained proper permission from their employers for the transfer of rights under this agreement, if those employers own any copyright in the manuscript. In addition, the authors assume any and all responsibility for possible copyright infringements of these employers, exempting Advances in Global Innovation & Technology (@_GIT) from any and all liability in this regard.
- The authors assume all responsibility for the content of the work, including the due and necessary authorizations for the disclosure of data collected and results obtained, exempting the Journal of Advances in Global Innovation & Technology (@_GIT) from any and all liability in this regard.
