TINA: Plataforma Web de Apoio a Pesquisadores para Análise de Corpora Textuais com PLN
Resumo
Textual corpus analysis often requires researchers to combine multiple tools for data preparation, linguistic processing, semantic analysis, and visualization. This paper presents TINA, a Web platform that organizes corpora as independent datasets and integrates language identification, named entity recognition, multilingual embeddings, keyword extraction, topic modeling, KWIC, LIWC, and interactive visualizations. The platform combines a FastAPI backend, MongoDB persistence, and a Next.js interface. A proof of concept using a toxic subset of the Brazilian Portuguese ToLD-Br corpus processed 9,152 unique documents, of which 84.23% were directly identified as Portuguese, while uncertain, unknown, and other-language predictions illustrated the need for explicit uncertainty handling when processing short and noisy texts.
Palavras-chave:
Natural Language Processing, Corpus Analysis, Topic Modeling, Text Analysis, Research Tool, Language Identification
Referências
Brigido Vizeu Camargo and Ana Maria Justo. 2013. IRAMUTEQ: um software gratuito para análise de dados textuais. Temas em Psicologia 21, 2, 513–518. DOI: 10.9788/TP2013.2-16
Ricardo Campos, Vitor Mangaravite, Arian Pasquali, Alipio M. Jorge, Celia Nunes, and Adam Jatowt. 2020. YAKE! Keyword extraction from single documents using multiple local features. Information Sciences 509 (2020), 257–289. DOI: 10.1016/j.ins.2019.09.013
Isaac Caswell, Theresa Breiner, Daan van Esch, and Ankur Bapna. 2020. Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus. arXiv preprint arXiv:2010.14571 (2020). [link]
Karen Gomes, Jussara M Almeida, Marcos André Gonçalves, and Fabrício Benevenuto. 2026. Medição e Análise do Discurso Tóxico Contra Deputadas Federais Brasileiras na Plataforma X. In Brazilian Workshop on Social Network Analysis and Mining (BraSNAM). SBC, 161–174.
Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT. DOI: 10.5281/zenodo.4461265
Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022). DOI: 10.48550/arXiv.2203.05794
Koichi Higuchi. 2017. New Quantitative Text Analytical Method and KH Coder Software. Japanese Sociological Review 68, 3 (2017), 334–350. DOI: 10.4057/jsr.68.334
Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. DOI: 10.5281/zenodo.1212303
Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hervé Jégou, and Tomas Mikolov. 2016. FastText.zip: Compressing text classification models. arXiv preprint arXiv:1612.03651 (2016).
Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of Tricks for Efficient Text Classification. arXiv preprint arXiv:1607.01759 (2016). [link]
Daniel Jurafsky and James H. Martin. 2025. Speech and Language Processing (3rd ed. draft ed.). [link]
João Augusto Leite, Diego Silva, Kalina Bontcheva, and Carolina Scarton. 2020. Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 914–924. DOI: 10.18653/v1/2020.aacl-main.91
H. P. Luhn. 1960. Keyword-in-context index for technical literature. American Documentation 11, 4 (1960), 288–295. DOI: 10.1002/asi.5090110403
Marco Lui and Timothy Baldwin. 2014. Accurate Language Identification of Twitter Messages. In Proceedings of the 5th Workshop on Language Analysis for Social Media. Association for Computational Linguistics, 17–25. DOI: 10.3115/v1/W14-1303
James W. Pennebaker, Ryan L. Boyd, Kayla Jordan, and Kate Blackburn. 2015. The Development and Psychometric Properties of LIWC2015. Technical Report. University of Texas at Austin. DOI: 10.15781/T29G6Z
Nils Reimers and Iryna Gurevych. 2020. Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. In Proceedings of EMNLP. Association for Computational Linguistics, 4512–4525. DOI: 10.18653/v1/2020.emnlpmain.365
Murilo U Ribeiro, Kênia C Gonçalves, M Renato Filho, Tomaz C Lima, Marcos A Gonçalves, and Jussara M Almeida. 2026. Discurso de Influenciadores Voltados ao Publico Infantojuvenil no Instagram: Uma Comparaçao Brasil e Estados Unidos. In Brazilian Workshop on Social Network Analysis and Mining (BraSNAM). SBC, 122–135.
Ghivvago Damas Saraiva, Rafael Anchiêta, Francisco Assis Ricarte Neto, and Raimundo Moura. 2021. A Semi-Supervised Approach to Detect Toxic Comments. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021). INCOMA Ltd., 1261–1267.
Stéfan Sinclair and Geoffrey Rockwell. 2016. Voyant Tools. [link]
Silvia Terragni, Elisabetta Fersini, Bruno Giovanni Galuzzi, Pietro Tropeano, and Antonio Candelieri. 2021. OCTIS: Comparing and Optimizing Topic models is Simple!. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, 263–270. DOI: 10.18653/v1/2021.eacl-demos.31
Guillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau, Vishrav Chaudhary, Francisco Guzmán, Armand Joulin, and Edouard Grave. 2020. CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, 4003–4012. [link]
Ricardo Campos, Vitor Mangaravite, Arian Pasquali, Alipio M. Jorge, Celia Nunes, and Adam Jatowt. 2020. YAKE! Keyword extraction from single documents using multiple local features. Information Sciences 509 (2020), 257–289. DOI: 10.1016/j.ins.2019.09.013
Isaac Caswell, Theresa Breiner, Daan van Esch, and Ankur Bapna. 2020. Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus. arXiv preprint arXiv:2010.14571 (2020). [link]
Karen Gomes, Jussara M Almeida, Marcos André Gonçalves, and Fabrício Benevenuto. 2026. Medição e Análise do Discurso Tóxico Contra Deputadas Federais Brasileiras na Plataforma X. In Brazilian Workshop on Social Network Analysis and Mining (BraSNAM). SBC, 161–174.
Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT. DOI: 10.5281/zenodo.4461265
Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022). DOI: 10.48550/arXiv.2203.05794
Koichi Higuchi. 2017. New Quantitative Text Analytical Method and KH Coder Software. Japanese Sociological Review 68, 3 (2017), 334–350. DOI: 10.4057/jsr.68.334
Matthew Honnibal, Ines Montani, Sofie Van Landeghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. DOI: 10.5281/zenodo.1212303
Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hervé Jégou, and Tomas Mikolov. 2016. FastText.zip: Compressing text classification models. arXiv preprint arXiv:1612.03651 (2016).
Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of Tricks for Efficient Text Classification. arXiv preprint arXiv:1607.01759 (2016). [link]
Daniel Jurafsky and James H. Martin. 2025. Speech and Language Processing (3rd ed. draft ed.). [link]
João Augusto Leite, Diego Silva, Kalina Bontcheva, and Carolina Scarton. 2020. Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 914–924. DOI: 10.18653/v1/2020.aacl-main.91
H. P. Luhn. 1960. Keyword-in-context index for technical literature. American Documentation 11, 4 (1960), 288–295. DOI: 10.1002/asi.5090110403
Marco Lui and Timothy Baldwin. 2014. Accurate Language Identification of Twitter Messages. In Proceedings of the 5th Workshop on Language Analysis for Social Media. Association for Computational Linguistics, 17–25. DOI: 10.3115/v1/W14-1303
James W. Pennebaker, Ryan L. Boyd, Kayla Jordan, and Kate Blackburn. 2015. The Development and Psychometric Properties of LIWC2015. Technical Report. University of Texas at Austin. DOI: 10.15781/T29G6Z
Nils Reimers and Iryna Gurevych. 2020. Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. In Proceedings of EMNLP. Association for Computational Linguistics, 4512–4525. DOI: 10.18653/v1/2020.emnlpmain.365
Murilo U Ribeiro, Kênia C Gonçalves, M Renato Filho, Tomaz C Lima, Marcos A Gonçalves, and Jussara M Almeida. 2026. Discurso de Influenciadores Voltados ao Publico Infantojuvenil no Instagram: Uma Comparaçao Brasil e Estados Unidos. In Brazilian Workshop on Social Network Analysis and Mining (BraSNAM). SBC, 122–135.
Ghivvago Damas Saraiva, Rafael Anchiêta, Francisco Assis Ricarte Neto, and Raimundo Moura. 2021. A Semi-Supervised Approach to Detect Toxic Comments. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021). INCOMA Ltd., 1261–1267.
Stéfan Sinclair and Geoffrey Rockwell. 2016. Voyant Tools. [link]
Silvia Terragni, Elisabetta Fersini, Bruno Giovanni Galuzzi, Pietro Tropeano, and Antonio Candelieri. 2021. OCTIS: Comparing and Optimizing Topic models is Simple!. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, 263–270. DOI: 10.18653/v1/2021.eacl-demos.31
Guillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau, Vishrav Chaudhary, Francisco Guzmán, Armand Joulin, and Edouard Grave. 2020. CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, 4003–4012. [link]
Publicado
27/10/2026
Como Citar
GOMES, Karen et al.
TINA: Plataforma Web de Apoio a Pesquisadores para Análise de Corpora Textuais com PLN. In: WORKSHOP DE FERRAMENTAS E APLICAÇÕES - SIMPÓSIO BRASILEIRO DE SISTEMAS MULTIMÍDIA E WEB (WEBMEDIA), 32. , 2026, Lavras/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 202-205.
ISSN 2596-1683.
DOI: https://doi.org/10.5753/webmedia_estendido.2026.34660.
