Artificial Neural Network Deployment GPU platform in Applied Feelings Analysis of Texts

• Cristiano Alex Künas UNIJUI
• Leandro Perius Heck UNIJUI
• Edson Luiz Padoin UNIJUI

DOI: https://doi.org/10.5753/eradrs.2020.10751

Abstract

This article proposes a parallelization of an Artificial Neural Network on GPU Platform for application in the analysis of the polarity of feelings expressed in text and / or posts. Implementation will be used Recurrent Neural Networks type Long Short-Term Memory as Artificial Neural Networks can assist in automatically extracting feelings or sense of sentences. With the implementation of the proposal in real case from the training with IMDb Review Dataset, which has 50,000 records expected good accuracy in the results.

Keywords: Dedicated architectures and Specific (GPUs, FPGAs, and others)

References

Brum, H. B. (2015). Análise de sentimentos para o português usando redes neurais recursivas. Monografia (Bacharel em Ciência da Computação), Universidade Federal do Pampa, Alegrete, Brazil.

dos Santos, I. P. P. (2017). Análise de sentimento usando redes neurais de convolução. Dissertação (Mestrado em Engenharia Eletrônica), Universidade do Estado do Rio de Janeiro, Rio de Janeiro, Brazil.

Hemalatha, I., Varma, G. S., and Govardhan, A. (2013). Sentiment analysis tool using machine learning algorithms. International Journal of Emerging Trends & Technology in Computer Science (IJETTCS), 2(2):105–109.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.

Kalaivani, P. and Shunmuganathan, K. (2013). Sentiment classification of movie reviews by supervised machine learning approaches. Indian Journal of Computer Science and Engineering, 4(4):285–292.

Liu, B. et al. (2010). Sentiment analysis and subjectivity. Handbook of natural language processing, 2(2010):627–666.

Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., and Potts, C. (2011). Learning word vectors for sentiment analysis. In Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies-volume 1, pages 142–150. Association for Computational Linguistics.

Olah, C. (2015). Understanding lstm networks. URL http://colah. github. io/posts/2015-08- Understanding-LSTMs.

Pang, B., Lee, L., and Vaithyanathan, S. (2002). Thumbs up?: sentiment classification using machine learning techniques. In Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, pages 79–86. Association for Computational Linguistics.

Santos, L. M., Esmin, A. A. A., Zambalde, A. L., and Nobre, F. M. (2010). Twitter, análise de sentimento e desenvolvimento de produtos: Quanto os usuários est˜ao expressando suas opini˜oes? Prisma. com, (13):159–170.

Sharma, R., Nigam, S., and Jain, R. (2014). Opinion mining of movie reviews at document level. arXiv preprint arXiv:1408.3829.

Tripathi, G. and Naganna, S. (2015). Feature selection and classification approach for sentiment analysis. Machine Learning and Applications: An International Journal, 2(2):1–16.