Document Type : Original Article


1 Department of Computer Engineering, Technical and Vocational University,(TVU), Tehran, Iran;

2 Department of Computer Engineering, Technical and Vocational University,(TVU), Tehran, Iran


With the advent of the Web today, users' opinions can be incorporated into a variety of applications. Automated methods have been developed to derive users' general sense from these textual comments, often known as sentiment analysis, and aim to determine the polarity of a text relative to a subject. One of the challenges is the inability to use one domain of data to analysis sentiment in another domain and the lack of sufficient labelled data in a particular domain. To address these challenges, multi-domain sentiment analysis systems have been developed. This paper propose Bi-GRU Capsule ensemble approaches for multi-domain sentiment classification to address the mentioned issues. Using a weighted score of Term-Frequency and Inverse Document Frequency degree and the initial polarity of the sample test data on each domain, a new aggregated score of final polarity is obtained. The DRANZIERA protocol is used for evaluation of the proposed model. The outcomes demonstrate the effectiveness of the proposed approach and also set a plausible starting point for future work


[1] Routray, P., Swain, C. K., & Mishra, S. P. (2013). A survey on sentiment analysis. International Journal of Computer Applications, 76(10).
[2] Torabian, B. (2016). Sentiment classification with case-base approach.
[3] Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1), 1-167.
[4] Bollegala, D., Weir, D., & Carroll, J. (2012). Cross-domain sentiment classification using a sentiment sensitive thesaurus. IEEE transactions on knowledge and data engineering, 25(8), 1719-1731.
[5] Gindl, S., Weichselbraun, A., & Scharl, A. (2010). Cross-domain contextualisation of sentiment lexicons.
[6] Zhang, H., Gan, W., & Jiang, B. (2014, September). Machine learning and lexicon based methods for sentiment classification: A survey. In 2014 11th web information system and application conference (pp. 262-265). IEEE.
[7] Shepelenko, O. (2017). Opinion mining and sentiment analysis using Bayesian and neural networks approaches (Doctoral dissertation, Master thesis, University of Tartu, Institute of Computer Science).
[8] Zhang, Z., Ye, Q., Zhang, Z., & Li, Y. (2011). Sentiment classification of Internet restaurant reviews written in Cantonese. Expert Systems with Applications, 38(6), 7674-7682.
[9] Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. arXiv preprint cs/0205070.
[10] Ye, Q., Zhang, Z., & Law, R. (2009). Sentiment classification of online reviews to travel destinations by supervised machine learning approaches. Expert systems with applications, 36(3), 6527-6535.         
[11] Prabowo, R., & Thelwall, M. (2009). Sentiment analysis: A combined approach. Journal of Informetrics, 3(2), 143-157.
[12] Riloff, E., Patwardhan, S., & Wiebe, J. (2006, July). Feature subsumption for opinion analysis. In Proceedings of the 2006 conference on empirical methods in natural language processing (pp. 440-448).
[13] Whitelaw, C., Garg, N., & Argamon, S. (2005, October). Using appraisal groups for sentiment analysis. In Proceedings of the 14th ACM international conference on Information and knowledge management (pp. 625-631).
[14] Turney, P. D. (2002). Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv preprint cs/0212032.
[15] Harb, A., Plantié, M., Dray, G., Roche, M., Trousset, F., & Poncelet, P. (2008, October). Web Opinion Mining: How to extract opinions from blogs?. In Proceedings of the 5th international conference on Soft computing as transdisciplinary science and technology (pp. 211-217).
[16] Miller, G. A., Beckwith, R., Fellbaum, C., Gross, D., & Miller, K. J. (1990). Introduction to WordNet: An on-line lexical database. International journal of lexicography, 3(4), 235-244.
[17] Kim, S. M., & Hovy, E. (2004). Determining the sentiment of opinions. In COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics (pp. 1367-1373).
[18] Hatzivassiloglou, V., & McKeown, K. (1997, July). Predicting the semantic orientation of adjectives. In 35th annual meeting of the association for computational linguistics and 8th conference of the european chapter of the association for computational linguistics (pp. 174-181).
[19] Blitzer, J., Dredze, M., & Pereira, F. (2007, June). Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In Proceedings of the 45th annual meeting of the association of computational linguistics (pp. 440-447).
[20] Ohana, B., Delany, S. J., & Tierney, B. (2012, September). A case-based approach to cross domain sentiment classification. In International Conference on Case-Based Reasoning (pp. 284-296). Springer, Berlin, Heidelberg.
[21] Dragoni, M., & Petrucci, G. (2018). A fuzzy-based strategy for multi-domain sentiment analysis. International Journal of Approximate Reasoning, 93, 59-73.
[22] Dragoni, M., & Petrucci, G. (2017). A neural word embeddings approach for multi-domain sentiment analysis. IEEE Transactions on Affective Computing, 8(4), 457-470.
[23] Shu, K., Sliva, A., Wang, S., Tang, J., & Liu, H. (2017). Fake news detection on social media: A data mining perspective. ACM SIGKDD explorations newsletter, 19(1), 22-36.
[24] Rojas-Barahona, L. M. (2016). Deep learning for sentiment analysis language and linguistics. Compass 10: 701–719.
[25] Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., & Lew, M. S. (2016). Deep learning for visual understanding: A review. Neurocomputing, 187, 27-48.
[26] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
[27] Abdel-Hamid, O., Mohamed, A. R., Jiang, H., Deng, L., Penn, G., & Yu, D. (2014). Convolutional neural networks for speech recognition. IEEE/ACM Transactions on audio, speech, and language processing, 22(10), 1533-1545.
[28] Moreno Lopez, M., & Kalita, J. (2017). Deep Learning applied to NLP. arXiv e-prints, arXiv-1703.
[29] Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. (2011). Natural language processing (almost) from scratch. Journal of machine learning research, 12(ARTICLE), 2493-2537.
[30] Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019.
[31] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
[32] Olah, C. (2015). Understanding lstm networks.
[33] Kim, Y. (2014). Convolutional neural networks for sentence classification. CoRR abs/1408.5882. arXiv preprint arXiv:1408.5882.
[34] Severyn, A., & Moschitti, A. (2015, August). Twitter sentiment analysis with deep convolutional neural networks. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval (pp. 959-962).
[35] Tai, K. S., Socher, R., & Manning, C. D. (2015). Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075.
[36] Dragoni, M., Tettamanzi, A. G., & da Costa Pereira, C. (2016, May). Dranziera: an evaluation protocol for multi-domain opinion mining. In Tenth International Conference on Language Resources and Evaluation (LREC 2016) (pp. 267-272). European Language Resources Association (ELRA).
[37] Chollet, F. (2015). keras, GitHub. GitHub repository.
[38] Yogatama, D., Dyer, C., Ling, W., & Blunsom, P. (2017). Generative and discriminative text classification with recurrent neural networks (2017). arXiv preprint arXiv:1703.01898.
[39] Kim, J., Jang, S., Park, E., & Choi, S. (2020). Text classification using capsules. Neurocomputing, 376, 214-221.
[40] Rezaeinia, S. M., Ghodsi, A., & Rahmani, R. (2017). Improving the accuracy of pre-trained word embeddings for sentiment analysis. arXiv preprint arXiv:1711.08609.