Abstract
Stance detection and sentiment analysis are two important problems that have gained significant attention in recent time. While stance detection corresponds to detecting the attitude/position (i.e., favor, against, and none) of a person towards any specific event or topic, sentiment analysis deals with determining the opinion expressed by a person for a topic, event, product or a service (i.e., positive, negative, and neutral). We envisage these two problems to have a good correlation. For e.g., information about favor stance can help in the prediction of positive sentiment or negative sentiment can help in predicting the against stance and so on. Motivated by this, in our current work, we propose a multi-task deep neural framework to investigate whether sentiment helps in stance detection and the vice-versa. Our proposed method makes use of an attention-based shared representation for multi-task stance detection and sentiment analysis. We also deploy an attention mechanism to learn the joint-association between the words present in a tweet and a topic. We evaluate our proposed approach on the benchmark dataset of SemEval-2016 Task 6. The proposed multi-task approach yields higher performance compared to the state-of-the-art systems for both stance detection and sentiment analysis.
D. S. Chauhan and R. Kumar have equal contribution and are jointly the first author.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akakandelwa, A., Walubita, G.: Students social media use and its perceived impact on their social life: a case study of the University of Zambia (2018)
Augenstein, I., Vlachos, A., Bontcheva, K.: USFD at SemEval-2016 task 6: any-target stance detection on Twitter with autoencoders. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 389–393 (2016)
Dey, K., Shrivastava, R., Kaushik, S.: Twitter stance detection—a subjectivity and sentiment polarity inspired two-phase approach. In: 2017 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 365–372. IEEE (2017)
Wei, W., Zhang, X., Liu, X., Chen, W., Wang, T.: pkudblab at SemEval-2016 task 6: a specific convolutional neural network system for effective stance detection. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 384–388 (2016)
Sun, Q., Wang, Z., Zhu, Q., Zhou, G.: Stance detection with hierarchical attention network. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 2399–2409 (2018)
Dey, K., Shrivastava, R., Kaushik, S.: Topical stance detection for twitter: a two-phase LSTM Model using attention. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds.) ECIR 2018. LNCS, vol. 10772, pp. 529–536. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-76941-7_40
Nakov, P., Ritter, A., Rosenthal, S., Sebastiani, F., Stoyanov, V.: SemEval-2016 task 4: sentiment analysis in Twitter. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 1–18 (2016)
Nakov, P., Ritter, A., Rosenthal, S., Sebastiani, F., Stoyanov, V.: Evaluation measures for the SemEval-2016 task 4: sentiment analysis in Twitter (draft: Version 1.12). In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval 2016), San Diego, California, June. Association for Computational Linguistics (2016)
Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)
Dias, M., Becker, K.: Inf-ufrgs-opinion-mining at SemEval-2016 task 6: automatic generation of a training corpus for unsupervised identification of stance in tweets. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 378–383 (2016)
Krejzl, P., Steinberger, J.: UWB at SemEval-2016 task 6: stance detection. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 408–412 (2016)
Wojatzki, M., Zesch, T.: ltl. uni-due at SemEval-2016 task 6: stance detection in social media using stacked classifiers. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 428–433 (2016)
Zhang, Z., Lan, M.: ECNU at SemEval 2016 task 6: relevant or not? Supportive or not? A two-step learning system for automatic detecting stance in tweets. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 451–457 (2016)
Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X., Cherry, C.: SemEval-2016 task 6: detecting stance in tweets. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 31–41 (2016)
Acknowledgment
Asif Ekbal acknowledges the Young Faculty Research Fellowship (YFRF), supported by Visvesvaraya Ph.D. scheme of MeiTY, Government of India. The research reported here is also partially supported by Skymap Global India Private Limited”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chauhan, D.S., Kumar, R., Ekbal, A. (2019). Attention Based Shared Representation for Multi-task Stance Detection and Sentiment Analysis. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1143. Springer, Cham. https://doi.org/10.1007/978-3-030-36802-9_70
Download citation
DOI: https://doi.org/10.1007/978-3-030-36802-9_70
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36801-2
Online ISBN: 978-3-030-36802-9
eBook Packages: Computer ScienceComputer Science (R0)