Abstract
In the changing social and economic environment, organisations are keen to act promptly and appropriately to changes. Sentiment analysis can be applied to social media data to capture timely information of new events and the corresponding public opinions. However, currently both the social topics and trending words are changing just as rapidly as the target topics and domains that organisations are interested in investigating. Therefore, there is a need for a well-trained sentiment analysis model able to handle out-of-domain input. Current solutions mainly focus on using domain adaptation techniques, but these solutions require domain-specific data and inevitably introduce extra overheads. To tackle this challenge, we propose a green Artificial Intelligence (AI) solution for a sentiment analysis pipeline (GreenSAP) to gain a better understanding of the changing public opinions on social media. Specifically, we propose to leverage the expressively powerful capability of the pre-trained Transformer encoder, and make use of several publicly-available sentiment analysis datasets from various domains and scenarios to develop a pipeline model. A sarcasm detection model is also included to eliminate false positive predictions. In experiments, this model significantly outperforms its competitors on three public benchmark datasets and on two of our labelled out-of-domain datasets for real-world applications.
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
Similar content being viewed by others
Notes
- 1.
In this work, we focus on the “aspect-term” setting where \(t\in s\) rather than the “aspect-category” setting with pre-set aspect categories.
References
Agarwal, A., Xie, B., Vovsha, I., Rambow, O., Passonneau, R.J.: Sentiment analysis of Twitter data. In: LSM, pp. 30–38 (2011)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR, pp. 1–15 (2015)
Castro, S., Hazarika, D., Pérez-Rosas, V., Zimmermann, R., Mihalcea, R., Poria, S.: Towards multimodal sarcasm detection (an _obviously_ perfect paper). arXiv preprint arXiv:1906.01815 (2019)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)
Dong, L., Wei, F., Tan, C., Tang, D., Zhou, M., Xu, K.: Adaptive recursive neural network for target-dependent Twitter sentiment classification. In: ACL (2014)
Fang, X., Zhan, J.: Sentiment analysis using product review data. J. Big Data 2(1), 1–14 (2015). https://doi.org/10.1186/s40537-015-0015-2
Ghosh, D., Vajpayee, A., Muresan, S.: A report on the 2020 sarcasm detection shared task. arXiv preprint arXiv:2005.05814 (2020)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: Exploiting document knowledge for aspect-level sentiment classification. In: ACL, pp. 579–585 (2018)
Hee, C.V., Lefever, E., Hoste, V.: SemEval-2018 task 3: irony detection in English tweets. In: SemEval@NAACL-HLT, pp. 39–50 (2018)
Jo, Y., Oh, A.H.: Aspect and sentiment unification model for online review analysis. In: WSDM, pp. 815–824 (2011)
Joshi, A., Bhattacharyya, P., Carman, M.J.: Automatic sarcasm detection: a survey. CSUR 50(5), 1–22 (2017)
Liu, B.: Sentiment analysis and opinion mining. Synth. Lect. Hum. Lang. Technol. 5(1), 1–167 (2012)
Liu, B.: Sentiment Analysis - Mining Opinions, Sentiments, and Emotions. Cambridge University Press, Cambridge (2015)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Pontiki, M., et al.: SemEval-2016 task 5: aspect based sentiment analysis. In: 1SemEval 2016 (2016)
Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I., Manandhar, S.: SemEval-2014 task 4: aspect based sentiment analysis. In: SemEval 2014, August 2014
Potamias, R.A., Siolas, G., Stafylopatis, A.G.: A transformer-based approach to irony and sarcasm detection. Neural Comput. Appl. 32(23), 17309–17320 (2020). https://doi.org/10.1007/s00521-020-05102-3
Rietzler, A., Stabinger, S., Opitz, P., Engl, S.: Adapt or get left behind: domain adaptation through BERT language model finetuning for aspect-target sentiment classification. In: LREC, pp. 4933–4941 (2020)
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. arXiv preprint arXiv:1907.10597 (2019)
Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP, pp. 1631–1642 (2013)
Sun, C., Huang, L., Qiu, X.: Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. In: NAACL-HLT, pp. 380–385 (2019)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998–6008 (2017)
Wang, K., Shen, W., Yang, Y., Quan, X., Wang, R.: Relational graph attention network for aspect-based sentiment analysis. In: ACL, pp. 3229–3238 (2020)
Wang, Z., Wu, Z., Wang, R., Ren, Y.: Twitter sarcasm detection exploiting a context-based model. In: Wang, J., et al. (eds.) WISE 2015. LNCS, vol. 9418, pp. 77–91. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-26190-4_6
Wiebe, J., Bruce, R., O’Hara, T.P.: Development and use of a gold-standard data set for subjectivity classifications. In: ACL, pp. 246–253 (1999)
Zhang, L., Wang, S., Liu, B.: Deep learning for sentiment analysis: a survey. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 8(4), e1253 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Xie, M., Jiang, J., Shen, T., Wang, Y., Gerrard, L., Clarke, A. (2022). A Green Pipeline for Out-of-Domain Public Sentiment Analysis. In: Li, B., et al. Advanced Data Mining and Applications. ADMA 2022. Lecture Notes in Computer Science(), vol 13087. Springer, Cham. https://doi.org/10.1007/978-3-030-95405-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-95405-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95404-8
Online ISBN: 978-3-030-95405-5
eBook Packages: Computer ScienceComputer Science (R0)