ANÁLISE DE SENTIMENTOS DO TWITTER COM NAÏVE BAYES E NLTK

Augusto Weiand

Artigos de análise de dados e pesquisa acadêmica

v. 7 n. 2 (2016): Trajetória Multicursos

ANÁLISE DE SENTIMENTOS DO TWITTER COM NAÏVE BAYES E NLTK

Augusto Weiand

PDF do artigo completo

Enviado: 30 April 2024
Publicado: 30-04-2024

Resumo

Este artigo propõe um algoritmo de análise de sentimentos dos tweets do microblog Twitter, utilizando o modelo probabilístico de Naïve Bayes. Foram utilizados os dados pré-analisados de (Sanders, 2011) para a construção do corpus e posterior aplicação da análise e validação cruzada. Após, demonstramos o desenvolvimento do algoritmo seguindo a metodologia estudada nos artigos relacionados, utilizando também, as bibliotecas NLTK e Scikit-Learn para o auxílio na aplicação do algoritmo com a linguagem de programação python, medidas de acurácia e validação cruzada dos dados. Organizamos este artigo em sessões que abordam os trabalhos relacionados, a metodologia utilizada, o sistema de coleta de dados, a biblioteca NLTK, o modelo probabilístico Naïve Bayes e por fim, os resultados e os trabalhos futuros, nesta ordem.

Referências

ANJARIA, Malhar; GUDDETI, Ram Mahana Reddy. Influence factor based opinion mining of Twitter data using supervised learning. Communication Systems and Networks (COMSNETS), Sixth International Conference on. Disponível em: http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6734907 acesso em: 10/06/14. Acesso em: 2 mar. 2017.
BARBOSA, Luciano; FENG, Junlan. Robust sentiment detection on Twitter from biased and noisy data. Proceedings of the 23rd International Conference on Computational Linguistics: Posters, Pages 36-44 Association for Computational Linguistics Stroudsburg, PA, USA.
BRAGA, Antônio De Pádua; CARVALHO, André Ponce De Leon E De; LUDERMIR, Teresa Bernarda. Redes Neurais Artificiais: Teoria e Aplicações. Editora LTC, 2000.
ESPINOSA, Kurt Junshean; LLAGUNO, Kevin; CARO, Jaime. Sentiment analysis of Facebook statuses using Naive Bayes classifier for language learning. Information, Intelligence, Systems and Applications (IISA), Fourth International Conference on. . Disponível em: http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6623713. Acesso em: 2 mar. 2017.
HAN, Jiawei; KAMBER, Micheline. Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers Inc. San Francisco, 2011.
JOACHIMS, T. Learning to classify texts using support vector machines: methods, theory and algorithms. Kluwer Academic Publishers, 2002.
JOLLIFFE I.T. Principal Component Analysis. Springer Series in Statistics, Springer, NY, 2002.
KIM, Kwang In; JUNG, Keechul; PARK, Se Hyun; KIM, Hang Joon. Support vector machines for texture classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002.
MANNING, Christopher D.; RAGHAVAN, Prabhakar; SCHÜTZE, Hinrich. An Introduction to Information Retrieval. Cambridge, England. Cambridge University Press. Disponível em: http://nlp.stanford.edu/IR-book/pdf/irbookonlinereading.pdf. Acesso em: 2 mar. 2017.
MITCHELL, T. Machine Learning. McGraw Hill, 1997.
NLTK. Natural Language Processing with Python. Disponível em: http://www.nltk.org/book/. Acesso em: 2 mar. 2017.
NOBLE, William Stafford. Support vector machine applications in computational biology. In: B. Schölkopf, K. Tsuda, and J.-P. Vert, editors, Kernel Methods in computational biology, pages 71–92. MIT Press, 2004.
PARIKH, Ravi; MOVASSATE, Matin. Sentiment Analysis of User-Generated Twitter Updates using Various Classification Techniques, Stanford University.
PEREIRA, Alice Theresinha Cybis; SCHMITT, Valdenise; DIAS, Maria Regina Alvares. Virtual learning environments. Virtual learning environments in different contexts, Ciência Moderna, Rio de Janeiro, 2007.
KOHAVI, Ron. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2 (IJCAI'95), Vol. 2. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1995, 1137-1143.
SANDERS, Niek. Twitter Sentiment Corpus. Disponível em: http://sandersanalytics.com/lab/twitter-sentiment/. Acesso em: 2 mar. 2017.
SCIKIT-LEARN. Machine Learning in Python. Disponível em: http://scikit-learn.org/stable/index.html. Acesso em: 2 mar. 2017.
TURNEY, Peter D.. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Pages 417-424. Association for Computational Linguistics (ACL), USA DOI 10.3115/1073083.1073153.

[1] ANJARIA, Malhar; GUDDETI, Ram Mahana Reddy. Influence factor based opinion mining of Twitter data using supervised learning. Communication Systems and Networks (COMSNETS), Sixth International Conference on. Disponível em: http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6734907 acesso em: 10/06/14. Acesso em: 2 mar. 2017.

[2] BARBOSA, Luciano; FENG, Junlan. Robust sentiment detection on Twitter from biased and noisy data. Proceedings of the 23rd International Conference on Computational Linguistics: Posters, Pages 36-44 Association for Computational Linguistics Stroudsburg, PA, USA.

[3] BRAGA, Antônio De Pádua; CARVALHO, André Ponce De Leon E De; LUDERMIR, Teresa Bernarda. Redes Neurais Artificiais: Teoria e Aplicações. Editora LTC, 2000.

[4] ESPINOSA, Kurt Junshean; LLAGUNO, Kevin; CARO, Jaime. Sentiment analysis of Facebook statuses using Naive Bayes classifier for language learning. Information, Intelligence, Systems and Applications (IISA), Fourth International Conference on. . Disponível em: http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6623713. Acesso em: 2 mar. 2017.

[5] HAN, Jiawei; KAMBER, Micheline. Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers Inc. San Francisco, 2011.

[6] JOACHIMS, T. Learning to classify texts using support vector machines: methods, theory and algorithms. Kluwer Academic Publishers, 2002.

[7] JOLLIFFE I.T. Principal Component Analysis. Springer Series in Statistics, Springer, NY, 2002.

[8] KIM, Kwang In; JUNG, Keechul; PARK, Se Hyun; KIM, Hang Joon. Support vector machines for texture classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002.

[9] MANNING, Christopher D.; RAGHAVAN, Prabhakar; SCHÜTZE, Hinrich. An Introduction to Information Retrieval. Cambridge, England. Cambridge University Press. Disponível em: http://nlp.stanford.edu/IR-book/pdf/irbookonlinereading.pdf. Acesso em: 2 mar. 2017.

[10] MITCHELL, T. Machine Learning. McGraw Hill, 1997.

[11] NLTK. Natural Language Processing with Python. Disponível em: http://www.nltk.org/book/. Acesso em: 2 mar. 2017.

[12] NOBLE, William Stafford. Support vector machine applications in computational biology. In: B. Schölkopf, K. Tsuda, and J.-P. Vert, editors, Kernel Methods in computational biology, pages 71–92. MIT Press, 2004.

[13] PARIKH, Ravi; MOVASSATE, Matin. Sentiment Analysis of User-Generated Twitter Updates using Various Classification Techniques, Stanford University.

[14] PEREIRA, Alice Theresinha Cybis; SCHMITT, Valdenise; DIAS, Maria Regina Alvares. Virtual learning environments. Virtual learning environments in different contexts, Ciência Moderna, Rio de Janeiro, 2007.

[15] KOHAVI, Ron. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2 (IJCAI'95), Vol. 2. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1995, 1137-1143.

[16] SANDERS, Niek. Twitter Sentiment Corpus. Disponível em: http://sandersanalytics.com/lab/twitter-sentiment/. Acesso em: 2 mar. 2017.

[17] SCIKIT-LEARN. Machine Learning in Python. Disponível em: http://scikit-learn.org/stable/index.html. Acesso em: 2 mar. 2017.

[18] TURNEY, Peter D.. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Pages 417-424. Association for Computational Linguistics (ACL), USA DOI 10.3115/1073083.1073153.