Abstract
Deep learning has revolutionized the way valuable insights are discovered from the data in predictive modelling. It exploits the features in the dataset by gradually moving up the granularity level in each iteration feeding the results to the immediate upper layer resulting in significant performance boost. Though deep neural networks ace in the field of predictive modelling yet it has several shortcomings which need to be catered to. The black box nature of neurals, plethora of hyper-parameters to tune and its reluctance to converge faster on smaller datasets renders it discouraging sometimes. Surface classifiers address these issues though with a compromise on the performance. Considering the shortcomings of the two aforementioned techniques, super learners harness the power of both the techniques by developing an amalgam of diverse learning algorithms. Inspired by this notion, this paper proposes a novel EDSL (Emoji based Deep Super Learner) that fits surface classifiers in a deep learning architecture to perform emoji based sentiment classification. It exploits the simplicity of surface classifiers and the power of deep neural networks achieving performance competitive to the later. Experiments prove that the proposed approach is highly adaptable and has better performance over individual surface learners and deep neural networks to classify text having emojis as key features.
All authors have equally contributed in the work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barbieri, F., Ballesteros, M., Saggion, H.: Are emojis predictable? arXiv, vol. 2, pp. 105–111 (2017)
Barbieri, F., Ronzano, F., Saggion, H.: What does this emoji mean? A vector space skip-gram model for twitter emojis. In: Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016, pp. 3967–3972 (2016)
Coman, A.C., Zara, G., Nechaev, Y., Moschitti, A.: Exploiting Deep Neural Networks for Tweet-Based Emoji Prediction, pp. 116–128 (2018)
Debnath, A., Pinnaparaju, N., Shrivastava, M., Varma, V., Augenstein, I.: Semantic textual similarity of sentences with emojis. In: The Web Conference 2020 - Companion of the World Wide Web Conference, WWW 2020, April, pp. 426–430 (2020). https://doi.org/10.1145/3366424.3383758
Duan, X., Ji, T., Qian, W.: Twitter US Airline Recommendation Prediction (2016). http://cs229.stanford.edu/proj2016spr/report/042.pdf
Eisner, B., Rocktäschel, T., Augenstein, I., Bosnjak, M., Riedel, S.: emoji2vec: learning emoji representations from their description. In: Proceedings of Fourth International Workshop on Natural Language Processing for Social Media, pp. 48–54 (2016). https://doi.org/10.18653/v1/w16-6208
Go, A., Bhayani, R., Huang, L.: Twitter Sentiment Classification using Distant Supervision (2009)
Hallsmar, F., Palm, J.: Multi-class Sentiment Classification on Twitter using an Emoji Training Heuristic, pp. 1–27 (2016). https://kth.diva-portal.org/smash/get/diva2:927073/FULLTEXT01.pdf
Hussien, W.A., Al-Ayyoub, M., Tashtoush, Y.M., Al-Kabi, M.N.: On the use of emojis to train emotion classifiers. arXiv (2019)
Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: ACL-HLT 2011 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 142–150 (2011)
Mathew, S.: On Device Deep Neural Networks for Emoji and Reply Prediction, pp. 7818–7824 (2020)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations, ICLR 2013 - Workshop Track Proceedings, pp. 1–12 (2013)
Novak, P.K., Smailovi, J., Sluban, B., Mozeti, I.: Sentiment of Emojis, pp. 1–22 (2015). https://doi.org/10.1371/journal.pone.0144296
Priya, B.G.: Emoji based sentiment analysis using KNN. Int. J. Sci. Res. Rev. 07(04), 859–865 (2019)
Riekert, M., Riekert, M., Klein, A.: Simple baseline machine learning text classifiers for small datasets. SN Comput. Sci. 2(3), 1–16 (2021). https://doi.org/10.1007/s42979-021-00480-4
Science, D.: ScienceDirect. 132, 167–173 (2018). https://doi.org/10.1016/j.procs.2018.05.200
Young, S., Abdou, T., Bener, A.: Deep super learner: a deep ensemble for classification problems. In: Bagheri, E., Cheung, J.C.K. (eds.) Canadian AI 2018. LNCS (LNAI), vol. 10832, pp. 84–95. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-89656-4_7
Zhao, L., Zeng, C.: Using Neural Networks to Predict Emoji Usage from Twitter Data, pp. 1–6 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vashisht, G., Jailia, M., Goyal, V. (2022). A Novel Emoji Based Deep Super Learner (EDSL) for Sentiment Classification. In: Abraham, A., et al. Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021). SoCPaR 2021. Lecture Notes in Networks and Systems, vol 417. Springer, Cham. https://doi.org/10.1007/978-3-030-96302-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-96302-6_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96301-9
Online ISBN: 978-3-030-96302-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)