Multi-layers Convolutional Neural Network for Twitter Sentiment Ordinal Scale Classification

  • Muath ALALI
  • Nurfadhlina Mohd Sharef
  • Hazlina Hamdan
  • Masrah Azrifah Azmi Murad
  • Nor Azura Husin
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 700)

Abstract

Twitter sentiment analysis according to five points scales has attracted research interest due to its potential use in commercial and public social media application. A multi-point scale classification is a popular way used by many companies to evaluate the sentiment of product reviews (e.g. Alibaba, Amazon and eBay). Most of the classification approaches addressed this problem using traditional classification algorithm that requires expert knowledge to select the best features. Even though deep learning has been utilized, most of them employed a simple structure that not enough to capture the important features. In this paper, a complex structure of convolutional neural network (CNN) is proposed to classify the tweet into five-point scale and obtain a more several tweet representation. After a series of experiments with CNN including different hyperparameters and pooling strategies (Max and Average), we found that the best structure for our model is three convolutional layers, each one followed by average pooling layer. The proposed multi-layers convolutional neural network (MLCNN) model achieve the lowest Macro average mean absolute error (MAEM) and outperforms the state-of-the-art approach on tweet 2016 dataset for Ordinal classification. Experimental results show the ability of average pooling to preserve significant features that provide more expressiveness to ordinal scale.

Keywords

Deep learning Convolutional neural network (CNN) Twitter sentiment analysis (TSA) Ordinal classification Text classification Sentiment analysis (SA) 

References

  1. 1.
    Pang, B., Lee, L.: Opinion Mining And Sentiment Analysis, vol. 1, no. 2 (2008)Google Scholar
  2. 2.
    Kim, Y.: Convolutional Neural Networks for Sentence Classification (2014). arXiv:1408.5882
  3. 3.
    Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp. 655–665 (2014)Google Scholar
  4. 4.
    Severyn, A., Moschitti, A.: Twitter sentiment analysis with deep convolutional neural networks. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’15), pp. 959–962 (2015)Google Scholar
  5. 5.
    Mohammad, S.M., Kiritchenko, S., Zhu, X.: NRC-Canada: building the state-of-the-art in sentiment analysis of tweets (2013)Google Scholar
  6. 6.
    Pak, A., Paroubek, P.: Twitter as a corpus for sentiment analysis and opinion mining. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation, pp. 1320–1326 (2010)Google Scholar
  7. 7.
    Nakov, P., Ritter, A., Rosenthal, S., Sebastiani, F.: SemEval-2016 Task 4: sentiment analysis in Twitter (2016)Google Scholar
  8. 8.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. NIPS, pp. 1–9 (2013)Google Scholar
  9. 9.
    Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference On Empirical Methods In Natural Language Processing, pp. 1532–1543 (2014)Google Scholar
  10. 10.
    Balikas, G., Amini, M.: TwiSE at SemEval-2016 Task: Twitter sentiment classification. In: International Workshop on Semantic Evaluation 2016, pp. 85–91 (2016)Google Scholar
  11. 11.
    Lango, M., Brzezinski, D., Stefanowski, J.: PUT at SemEval-2016 Task 4 : The ABC of Twitter sentiment analysis. In: International Workshop on Semantic Evaluation 2016, pp. 131–137 (2016)Google Scholar
  12. 12.
    Esuli, A., Faedo, I.A., Moruzzi, G.: ISTI-CNR at SemEval-2016 Task 4: quantification on an ordinal scale. In: International Workshop on Semantic Evaluation 2016. Accept., pp. 92–95 (2016)Google Scholar
  13. 13.
    Florean, C., Bejenaru, O., Apostol, E., Ciobanu, O., Iftene, A., Trandab, D.: SentimentalITsts at SemEval-2016 Task 4: building a Twitter sentiment analyzer in your backyard, pp. 248–251 (2016)Google Scholar
  14. 14.
    Zhou, Y., Zhang, Z., Lan, M.: ECNU at SemEval-2016 Task 4 : An empirical investigation of traditional NLP features and word embedding features for sentence-level and topic-level sentiment analysis in Twitter. In: International Workshop on Semantic Evaluation 2016, pp. 256–261 (2016)Google Scholar
  15. 15.
    Vilares, D., Doval, Y., Alonso, M.A., Carlos, G.: LyS at SemEval-2016 Task 4 : exploiting neural activation values for twitter sentiment classification and quantification. In: International Workshop on Semantic Evaluation 2016, pp. 79–84 (2016)Google Scholar
  16. 16.
    Stojanovski, D., Strezoski, G., Madjarov, G., Dimitrovski, I.: Finki at SemEval-2016 Task 4: deep learning architecture for Twitter sentiment analysis. In: International Workshop on Semantic Evaluation 2016. Accept., pp. 154–159, (2016)Google Scholar
  17. 17.
    He, Y., Yu, L., Yang, C., Lai, K.R., Liu, W.: YZU-NLP team at SemEval-2016 Task 4: ordinal sentiment classification using a recurrent convolutional network, pp. 256–260 (2016)Google Scholar
  18. 18.
    Ruder, S., Ghaffari, P., Breslin, J.G.: INSIGHT-1 at SemEval-2016 Task 4: convolutional neural networks for sentiment classification and quantification. In: International Workshop on Semantic Evaluation 2016. Accept., pp. 178–182 (2016)Google Scholar
  19. 19.
    Collobert, R., et al.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)MATHGoogle Scholar
  20. 20.
    Yann, L., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  21. 21.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning, no. 3, pp. 807–814 (2010)Google Scholar
  22. 22.
    Srivastava, N., Geoffrey, H., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout : a simple way to prevent neural networks from overfitting, vol. 15, pp. 1929–1958 (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Muath ALALI
    • 1
  • Nurfadhlina Mohd Sharef
    • 1
  • Hazlina Hamdan
    • 1
  • Masrah Azrifah Azmi Murad
    • 1
  • Nor Azura Husin
    • 1
  1. 1.Faculty of Computer Science and Information Technology, Intelligent Computing Research GroupUnversiti Putra Malaysia UPM SerdangSelangorMalaysia

Personalised recommendations