A Sentiment Polarity Classifier for Regional Event Reputation Analysis
Abstract
It is important to analyze reputation or demands for regional events, such as school festivals. In our previous works, we proposed sentiment polarity classification based on bag-of-words models and found that the traditional models were poor at classifying negative tweets. To improve the performance, we employed several classifier models based on deep learning models. In this paper, we described how to improve the performance of the sentiment polarity classification using deep learning models. We compared the performance of four models in terms of the classification accuracy and the training speed. As a result, we found that the CNN-based model, three words convolutions, was best among the four models. As the application, we also described the overview of a system based on the classifiers, which supports to analyze regional event reputation. We showed a case of a regional event analysis of a school festival by using our system.
References
T. Ohbe, T. Ozono, and T. Shintani, “Developing a sentiment polarity visualization system for local event information analysis,” in Advanced Applied Informatics (IIAIAAI), 2016 5th IIAI International Congress on. IEEE, 2016, pp. 19–24.
J. Foley, M. Bendersky, and V. Josifovski, “Learning to extract local events from the web,” in Proceedings of the 38th Annual ACM SIGIR Conference. ACM, 2015, pp. 423–432.
T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” in Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States., 2013, pp. 3111–3119.
A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification,” arXiv preprint arXiv:1607.01759, 2016.
P. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching word vectors with subword information,” arXiv preprint arXiv:1607.04606, 2016.
Q. V. Le and T. Mikolov, “Distributed representations of sentences and documents.” in ICML, vol. 14, 2014, pp. 1188–1196.
Y. Kim, “Convolutional neural networks for sentence classification,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, October 2014, pp. 1746–1751.
A. Severyn and A. Moschitti, “Twitter sentiment analysis with deep convolutional neural networks,” in Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, ser. SIGIR ’15. ACM, 2015, pp. 959–962.
K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using rnn encoder–decoder for statistical machine translation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 2014, pp. 1724–1734.
X. Wang, F. Wei, X. Liu, M. Zhou, and M. Zhang, “Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach,” in Proceedings of CIKM ’11, 2011, pp. 1031–1040.
B. Vincent, L. Xu, P. Chesley, and R. Srhari, “Using verbs and adjectives to automatically classify blog sentiment,” in Proceedings of AAAI-CAAW-06, 2006, pp. 27–29.
W. Wei and J. A. Gulla, “Sentiment learning on product reviews via sentiment ontology tree,” in Proceedings of ACL ’10, 2010, pp. 404–413.
Y. Terazawa, S. Shiramatsu, T. Ozono, and T. Shintani, “Sentiment polarity analysis for generating search result snippets based on paragraph vector,” in Advanced Applied Informatics (IIAI-AAI), 2015 IIAI 4th International Congress on. IEEE, 2015, pp. 109–114.
R. Li, K. H. Lei, R. Khadiwala, and K. C.-C. Chang, “Tedas: A twitter-based event detection and analysis system,” in Proceedings of ICDE 2012, 2012, pp. 1273–1276.
N. Hirata, S. Shiramatsu, T. Ozono, and T. Shintani, “A system for collecting tweets using event-based structuring of web contents,” International Journal of Computer Science and Artificial Intelligence, vol. 3, no. 2, pp. 50–58, 2013.
W. Sunayama, Y. Takama, Y. Nishihara, T. Kajinami, M. Kushima, and H. Tokunaga, “Practical application in development and use of mining tools with total environment for text data mining,” Transactions of the Japanese Society for Artificial Intelligence, vol. 29, pp. 100–112, 2014.
H. Takamura, T. Inui, and M. Okumura, “Extracting semantic orientations of words using spin model,” in Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, 2005, pp. 133–140.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proceedings of the 3rd International Conference on Learning Representations (ICLR), 2014.
