Identificação de Polaridade de Sentimento no Twitter Aplicada à Indústria Calçadista
Abstract
Diversos são os trabalhos relatados na literatura científica sobre classificação de sentimentos, com a extração de mensagens da plataforma de Twitter. Todavia verificou-se a inexistência de trabalhos focados especificamente referente a língua portuguesa para a área calçadista. O artigo mostra como é possível reconhecer opinião (positiva ou negativa) de consumidores em relação a área calçadista, utilizando de aprendizado de máquina a partir de tweets. Como modelo foi utilizado uma empresa de calçados da região Sul do Brasil. Foram coletados textos do Twitter, os quais foram pré-processados para a limpeza de termos irrelevantes, a extração de características para a obtenção de medidas e a diferenciação da polaridade. E por fim foi feita a identificação de qual classe o exemplar sob análise pertence com o uso de classificadores para o reconhecimento de polaridade. Os classificadores utilizados foram o Support Vector Machines (SVM), Multi-Layer Perceptron (MLP), Random Forest, Vizinhos mais próximos (KNN) e o Linear Discriminant Analysis (LDA). Os resultados mostraram que o melhor classificador para esse tipo de problema foi o MLP. Os resultados com o classificador MLP obtiveram especificidade de 78,5%, sensibilidade de 95,6% e uma acurácia de 86,0%.
References
SP. Chokkalingam and N. DuraiMurugan, “Sentiment analysis on GST in social mediausing R,” Journal of Advanced Research in Dynamical and Control Systems, Vol. 9, 2017.
Maria Giatsoglou, Vozalis, Manolis G. Vozalis, Konstantinos Diamantaras, Athena Vakali, George Sarigiannidis and Konstantinos Ch. Chatzisavvas, “Sentiment analysis leveraging emotions and word embeddings,” Expert Systems with Applications, vol. 69, pp. 241 – 224, 03 2017.
Said A. Salloum, Mostafa Al-Emran, Azza Abdel Monem and Khaled Shaalan, “A Survey of Text Mining in Social Media: Facebook and Twitter Perspectives,” Advances in Science, Technology and Engineering Systems Journal, vol. 2, no. 1, pp. 127-133, 2017.
Shilpy Gandharv, Vivek Richhariya and Vineet Richhariya, “Real Time Text Mining on Twitter Data,” International Journal of Computer Applications, vol. 178(3), pp. 24-28, 12 2017.
Ana Carolina E.S. Lima, Leandro Nunes de Castro and Luan M. Corchado, “A polarity analysis framework for Twitter messages,” Applied Mathematics and Computation, vol. 270, pp. 756 – 767, 11 2015.
Anderson Uilian Kauer and Viviane P. Moreira, “Using information retrieval for sentiment polarity prediction,” Expert Systems with Applications, vol. 61, pp. 282–289, 10 2016.
Abinash Tripathya, Ankit Agrawal and Santanu Kumar Rathc, “Classification of sentiment reviews using n-gram machine learning approach ,” Expert Systems with Applications, vol. 57, pp.117–126, 09 2016.
Torben Antrettera, Ivo Blohmb, Dietmar Grichnik and Joakim Wincenta, “Predicting new venture survival: A Twitter-based machine learning approach to measuring online legitimacy,” Journal of Business Venturing Insights, vol. 11, 06 2018.
Jose Ramon Saura, Pedro Palos-Sanchez and Antonio Grilo. “Detecting Indicators for Startup Business Success: Sentiment Analysis Using Text Data Mining,” Sustainability, vol. 11(3), 02 2019.
Bing Liu. “Sentiment analysis and subjectivity,” Handbook of Natural Language Processing. Second Edition, editors: N. Indurkhya and F. J. Damerau, 2010
Mika V. Mäntylä, Daniel Graziotin and Miikka Kuutila, “The evolution of sentiment analysis - A review of research topics, venues, and top cited papers,” Computer Science Review, vol. 27, pp. 16-32, 02 2018.
Mohammad Karim Sohrabi and Fatemeh Hemmatian, “An efficient preprocessing method for supervised sentiment analysis by converting sentences to numerical vectors: a twitter case study,” Multimedia Tools and Applications, vol. 78, pp. 24863–24882, 08 2019.
Dario Stojanovski1, Gjorgji Strezoski, Gjorgji Madjarov1, Ivica Dimitrovski and Ivan Chorbev1, “Deep neural network architecture for sentiment analysis and emotion identification of Twitter messages,” Multimedia Tools and Applications, vol. 77, pp. 32213–32242, 12 2018.
Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll and Manfred Stede, “Lexicon-based methods for sentiment analysis,” Comput Linguist, vol. 37, no.2, 2011.
Filipe N Ribeiro, Matheus Araújo, Pollyanna Gonçalves1, Marcos André Gonçalves and Fabrício Benevenuto, “SentiBench - a benchmark comparison of state-of-the-practice sentiment analysis methods,” EPJ Data Science, vol.5(1), 2016.
Symeon Symeonidis, Dimitrios Effrosynidis and Avi Arampatzis, “A comparative evaluation of pre-processing techniques and their interactions for twitter sentiment analysis,” Expert Systems with Applications, vol. 110, pp. 298–310, 11 2018.
Karine França de Souza, Moisés Henrique Ramos Pereira and Daniel Hasan Dalip, “UniLex: Método Léxico para Análise de Sentimentos Textuais sobre Conteúdo de Tweets em Português Brasileiro” Abakós, vol. 5, pp. 79–96, 05 2017.
Peiman Barnaghi1, Parsa Ghaffari2 and John G. Breslin1, “Opinion Mining and Sentiment Polarity on Twitter and Correlation between Events and Sentiment,” 2016 IEEE Second International Conference on Big Data Computing Service and Applications, 2016.
Vladimir Vargas-Calderóna and Jorge E. Camargo, “Characterization of citizens using word2vec and latent topic analysis in a large set of tweets,” Cities, vol. 92, pp. 187–196, 2019.
Mochamad and Dwi Andini Putri, “Algorithm application support vector machine with genetic algorithm optimization technique for selection features for the analysis of sentiment on twitter,” Journal of Theoretical and Applied Information Technology, vol. 84, no.3, 2016.
Donghwa Kim, Seo, Deokseong Seo and Pilsung Kang, “Multi-co-training for document classification using various document representations: TF–IDF, LDA, and Doc2Vec,” Information Sciences, vol. 477, pp. 15–29, 03 2018.
Akrivi Krouska, Christos Troussas and Maria Virvou, “Comparative evaluation of algorithms for sentiment analysis over social networking services,” Journal of Universal Computer Science, vol. 23, pp. 755-768, 2018.
M. Nivaashini, Soundariya, R. S. Soundariya and P. Thangaraj, “Comparative Analysis of Machine Learning Approaches for Twitter Sentiment Analysis,” Journal of Computational and Theoretical Nanoscience, vol. 15, pp. 1743–1749, 2018.
Zhao Jianqiang and Gui Xiaolin, “Comparison Research on Text Pre-processing Methods on Twitter Sentiment Analysis,” IEEE Access, vol. 5, pp. 2870–2879, 2017.
E. Suganya and S. Vijayarani, “Sentiment Analysis for Scraping of Product Reviews from Multiple Web Pages Using Machine Learning Algorithms,” Springer Nature Switzerland, vol. 941, pp. 677–685, 2020.
Zhao Jianqiang and Gui Xiaolin, “Deep Convolution Neural Networks for Twitter Sentiment Analysis,” IEEE Access, vol. 6, pp. 23253–23260, 01 2018.
Abhilash Mittal and Sanjay Patidar, “Sentiment Analysis on Twitter Data,” International Conference on Computer and Communications Management, 2019.
Tu Shouzhong and Huang Minlie, “Mining microblog user interests based on TextRank with TF-IDF factor,” The Journal of China Universities of Posts and Telecommunications, vol. 23(5), pp. 40–46, 10 2016.
Jitendra Kumar Rout, Kim-Kwang Raymond Choo, Amiya Kumar Dash, Sambit Bakshi, Sanjay Kumar Jena and Karen L. Williams, “A model for sentiment and emotion analysis of unstructured social media text,” Electronic Commerce Research, vol.18(1), pp. 181–199, 2017.
Andrew Webb, Statistical Pattern Recognition: Third Edition. Ltd. John Wiley and Sons: New mingYork, 2002.
Duda, Richard & Hart, Peter & G. Stork, David. Pattern Classification. John Wiley and Sons: New York, 2001.
Downloads
Published
How to Cite
Issue
Section
License
Declaração de originalidade e cessão de direitos autorais
Declaro que o presente artigo é original, não está sendo tendo sido submetido à publicação em qualquer outro periódico nacional ou internacional durante o processo de revisão. Através deste instrumento, em meu nome e em nome dos demais co-autores, porventura existentes, cedo os direitos autorais do referido artigo à revista SCIENTIA CUM INDUSTRIA. Contudo, a reprodução total ou parcial impressa ou eletrônica pode ser feita desde que o autor comunique oficialmente à revista. Declaro estar ciente de que a não observância deste compromisso submeterá o infrator a sanções e penas previstas na Lei de Proteção de Direitos Autorias. Declaro estar ciente de que a não observância deste compromisso submeterá o infrator a sanções e penas previstas na Lei de Proteção de Direitos Autorias (Nº9610, de 19/02/1998).
