In this paper, we study the problem of binary sentiment classification on a set of polar movie reviews. There are many models which have achieved state of the art performance, but one has to deal with the problem of tuning a large number of hyper-parameters. With the addition of the deep forest model as proposed by Zhi-Hua and Ji Feng, the number of hyper-parameters to be tuned is less and the architecture is still able to perform well. The goal of this paper is to use Word2Vec, FastText and Doc2Vec for creating word vector representation of the reviews which are then trained on a deep forest model. In order to further enhance the performance, the trained model is further trained on a different set of classifiers and as a result, a significant improvement in performance was noticed.

DeepForest, WordEmbeddings, Word2Vec, FastText, Doc2Vec, SVM

[1] Tulsi Jain, Kushagra Agarwal, Ronil Pancholia, "Sentiment Analysis Based on a Deep Stochastic Network and Active Learning", International Journal of Computer Sciences and Engineering, Vol.5, Issue.9, pp.1-6, 2017.
[2] M. M. Sutar, T. I. Bagban, "Applying Sentiment Analysis to Predict Rating and Classification of Text Review", International Journal of Computer Sciences and Engineering, Vol.6, Issue.7, pp.173-178, 2018.
[3] Static.ijcai.org. (2018). [online] Available at:
http://static.ijcai.org/proceedings-2017/0497.pdf
[Accessed 13 Jun. 2018].
[4] Arxiv.org. (2018). [online] Available at: https://arxiv.org/pdf/1702.08835.pdf [Accessed 13 Jun. 2018]
[5] Akhtar, M. S., Kumar, A., Ghosal, D., Ekbal, A., & Bhattacharyya, P. (2017). A multilayer perceptron based ensemble technique for fine-grained financial sentiment analysis. In Proceedings of the Conference on Empirical Methods on Natural Language Processing (EMNLP 2017).
[6] Akhtar, M. S., Kumar, A., Ekbal, A., & Bhattacharyya, P. (2016). A hybrid deep learning architecture for sentiment analysis. In Proceedings of the International Conference on Computational Linguistics (COLING 2016).
[7] Abdul-Mageed, M., & Ungar, L. (2017). EmoNet: Fine-grained emotion detection with gated recurrent neural networks. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2017)
[8] Cho, K., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2014).
[9] Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. (2011). Natural language processing (almost) from scratch. Journal of Machine Learning Research
[10] Guan, Z., Chen, L., Zhao, W., Zheng, Y., Tan, S., & Cai, D. (2016). Weakly-supervised deep learning for customer review sentiment classification. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI 2016)
[11] Dou, Z. Y. (2017). Capturing user and product Information for document level sentiment analysis with deep memory network. In Proceedings of the Conference on Empirical Methods on Natural Language Processing (EMNLP 2017).
[12] A. Hassan and A. Mahmood, "Deep Learning approach for sentiment analysis of short texts", 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), 2017.
[13] N. Zainuddin and A. Selamat, "Sentiment analysis using Support Vector Machine", 2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2014.
[14] Arxiv.org. (2018). [online] Available at: https://arxiv.org/pdf/1702.08835.pdf [Accessed 13 Jun. 2018].
[15] Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K. and Kuksa, P. (2018). Natural Language Processing (almost) from Scratch. [online] Arxiv.org. Available at: https://arxiv.org/abs/1103.0398 [Accessed 18 Aug. 2018].
[16] Mikolov, T., Chen, K., Corrado, G. and Dean, J. (2018). Efficient Estimation of Word Representations in Vector Space. [online] Arxiv.org. Available at: https://arxiv.org/abs/1301.3781 [Accessed 14 Jun. 2018].
[17] Mikolov, T., Chen, K., Corrado, G. and Dean, J. (2018). Efficient Estimation of Word Representations in Vector Space. [online] Arxiv.org. Available at: https://arxiv.org/abs/1301.3781 [Accessed 18 Aug. 2018].
[18] Joulin, A., Grave, E., Bojanowski, P. and Mikolov, T. (2018). Bag of Tricks for Efficient Text Classification. [online] Arxiv.org. Available at: https://arxiv.org/abs/1607.01759 [Accessed 18 Aug. 2018].
[19] Le, Q. and Mikolov, T. (2018). Distributed Representations of Sentences and Documents. [online] Arxiv.org. Available at: https://arxiv.org/abs/1405.4053 [Accessed 18 Aug. 2018].
[20] Medium. (2018). Chapter 3: Support Vector machine with Math. – Deep Math Machine learning.ai – Medium. [online] Available at: https://medium.com/deep-math-machine-learning-ai/chapter-3-support-vector-machine-with-math-47d6193c82be [Accessed 14 Jun. 2018].
[21] Hackerearth.com. (2018). Simple Tutorial on SVM and Parameter Tuning in Python and R | Machine Learning | HackerEarth Blog. [online] Available at: https://www.hackerearth.com/blog/machine-learning/simple-tutorial-svm-parameter-tuning-python-r/ [Accessed 14 Jun. 2018].
[22] Maas, A. (2018). Sentiment Analysis. [online] Ai.stanford.edu. Available at: http://ai.stanford.edu/~amaas/data/sentiment/ [Accessed 14 Jun. 2018].
[23] Maas, A., Daly, R., Pham, P., Huang, D., Ng, A. and Potts, C. (2018). Learning word vectors for sentiment analysis. [online] Dl.acm.org. Available at: https://dl.acm.org/citation.cfm?id=2002491 [Accessed 14 Jun. 2018].
[24] Zhou, Z. and Feng, J. (2018). Deep Forest. [online] Arxiv.org. Available at: https://arxiv.org/abs/1702.08835 [Accessed 18 Aug. 2018].