Abstract
Nuclear energy is one of controversial topics that affects people’s lives, and it is important for policy makers to analyze what people feel towards the subject. But manual analysis of related user-generated contents on social media platforms is a daunting task, and automatic data analysis and visualization come to help. So, in this research, we firstly developed a model for classifying the emotion of nuclear energy related tweets and another model for the aspect-based sentiment analysis of nuclear energy tweets using the BERT (Bidirectional Encoder Representations from Transformers). After that, we developed a prototype system for visualization of the analyzed results stored in the database. The user interface dashboards of the system allow users to monitor emotion and sentiment trends towards nuclear energy by analyzing recent nuclear energy tweets crawled weekly.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Benedetto, F., Tedeschi, A.: Big data sentiment analysis for brand monitoring in social media streams by cloud computing. In: Pedrycz, W., Chen, S.-M. (eds.) Sentiment Analysis and Ontology Engineering. SCI, vol. 639, pp. 341–377. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-30319-2_14
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019, pp. 4171–4186 (2018)
Kant, N., Puri, R., Yakovenko, N., Catanzaro, B.: Practical text classification with large pre-trained language models (2018). https://arxiv.org/pdf/1812.01207.pdf
Liu, Z., Na, J.-C.: Aspect-based sentiment analysis of nuclear energy tweets with attentive deep neural network. In: Dobreva, M., Hinze, A., Žumer, M. (eds.) ICADL 2018. LNCS, vol. 11279, pp. 99–111. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04257-8_9
Olaleye, S.A., Sanusi, I.T., Salo, J.: Sentiment analysis of social commerce: a harbinger of online reputation management. Int. J. Electron. Bus. 14(2) (2018). https://doi.org/10.1504/IJEB.2018.094864
Sayce, D.: The Number of tweets per day in 2020 (2020). https://www.dsayce.com/social-media/tweets-day/
Sun, C., Huang, L., Qiu, X.: Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. In: NAACL-HLT 2019, pp. 380–385 (2019)
NLP-text-emotion-dataset. https://github.com/lukasgarbas/nlp-text-emotion/tree/master/data
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Arumugam, S. et al. (2021). A Prototype System for Monitoring Emotion and Sentiment Trends Towards Nuclear Energy on Twitter Using Deep Learning. In: Ke, HR., Lee, C.S., Sugiyama, K. (eds) Towards Open and Trustworthy Digital Societies. ICADL 2021. Lecture Notes in Computer Science(), vol 13133. Springer, Cham. https://doi.org/10.1007/978-3-030-91669-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-91669-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91668-8
Online ISBN: 978-3-030-91669-5
eBook Packages: Computer ScienceComputer Science (R0)