An Analysis of Machine Learning Techniques to Prioritize Customer Service Through Social Networks
DOI:
https://doi.org/10.5753/jidm.2018.2049Keywords:
Sentiment Analysis, Deep Learning, LSTM, Social Networks, Customer ServiceAbstract
The large amount of opinionated data made available by social networks allows the extraction of valuable information for a variety of applications. Sentiment analysis is a powerful tool in this sense, allowing to identify and classify opinions in texts according to the predominant polarity exposed in them. An interesting use of this technique is for companies to rank the messages from their clients in order to identify and attend the most dissatisfied ones first, thus improving customer service. In this work, we evaluate the application of a range of different machine learning techniques (including two deep learning ones) to the sentiment analysis of tweets in Brazilian Portuguese, aiming customer service prioritization. Our results show that the deep learning models are able to classify tweets more efficiently in this context, compared to traditional machine learning ones.
Downloads
References
Alves, A. L. F., de Souza Baptista, C., Firmino, A. A., de Oliveira, M. G., and de Paiva, A. C. A spatial and temporal sentiment analysis approach applied to twitter microtexts. Journal of Information and Data Management 6 (2): 118, 2016.
Amora, P., Teixeira, E., Lima, M., Amaral, G., Cardozo, J., and Machado, J. A deep learning approach to prioritize customer service using social networks, 2017.
Balage Filho, P. P., Pardo, T. A., and Aluísio, S. M. An evaluation of the Brazilian Portuguese LIWC dictionary for sentiment analysis. In Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology (STIL). pp. 215–219, 2013.
Bojanowski, P., Grave, E., Joulin, A., and Mikolov, T. Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 , 2016.
Chollet, F. Keras, 2015. Accessed: 2017-05-22.
Dosciatti, M. M., Ferreira, L. P. C., and Paraiso, E. C. Identificando emoções em textos em português do brasil usando máquina de vetores de suporte em solução multiclasse. ENIAC-Encontro Nacional de Inteligência Artificial e Computacional. Fortaleza, Brasil, 2013.
Elman, J. L. Finding structure in time. Cognitive science 14 (2): 179–211, 1990.
Graves, A., Mohamed, A.-r., and Hinton, G. Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (icassp), 2013 ieee international conference on. IEEE, pp. 6645–6649, 2013.
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012.
Hochreiter, S., Bengio, Y., Frasconi, P., and Schmidhuber, J. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies, 2001.
Hochreiter, S. and Schmidhuber, J. Long short-term memory. Neural computation 9 (8): 1735–1780, 1997.
Lee, J. Y. and Dernoncourt, F. Sequential short-text classification with recurrent and convolutional neural networks. arXiv preprint arXiv:1603.03827 , 2016.
Liu, B. Sentiment Analysis - Mining Opinions, Sentiments, and Emotions. Cambridge University Press, 2015.
Liu, P., Qiu, X., and Huang, X. Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101 , 2016.
Mikolov, T., Chen, K., Corrado, G., and Dean, J. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 , 2013.
Mozer, M. C. A focused backpropagation algorithm for temporal. Backpropagation: Theory, architectures, and applications, 1995.
Olah, C. Understanding lstm networks, 2015. [Online; accessed 2017-04-26].
Pang, B. and Lee, L. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval 2 (1-2): 1–135, 2007.
Plank, B., Søgaard, A., and Goldberg, Y. Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss. arXiv preprint arXiv:1604.05529 , 2016.
Rojas-Barahona, L. M. Deep learning for sentiment analysis. Language and Linguistics Compass 10 (12): 701–719, 2016.
Socher, R., Perelygin, A., Wu, J. Y., Chuang, J., Manning, C. D., Ng, A. Y., Potts, C., et al. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the conference on empirical methods in natural language processing (EMNLP). Vol. 1631. Citeseer, pp. 1642, 2013.
Souza, M. and Vieira, R. Sentiment analysis on twitter data for portuguese language. In International Conference on Computational Processing of the Portuguese Language. Springer, pp. 241–247, 2012.
Taboada, M., Brooke, J., Tofiloski, M., Voll, K. D., and Stede, M. Lexicon-based methods for sentiment analysis. Computational Linguistics 37 (2): 267–307, 2011.
Tang, D., Wei, F., Yang, N., Zhou, M., Liu, T., and Qin, B. Learning sentiment-specific word embedding for twitter sentiment classification. In ACL (1). pp. 1555–1565, 2014.
Timmaraju, A. and Khanna, V. Sentiment analysis on movie reviews using recursive and recurrent neural network architectures. Semantic Scholar , 2015.
Yuan, Y. and Zhou, Y. Twitter sentiment analysis with recursive neural networks, 2015.
