Abstract
Nowadays, social networks, specially Twitter (now X), allow the spread of information about all topics; since this platform is completely open, there is little to none restriction on what a user can post, hence, creating a lack of confidence and trust on the information available. However, the information on Twitter sometimes have hidden meanings, as the users use metaphors to define their ideas. This paper analyzes and classifies a set of texts labeled as disaster and non-disaster, where those labeled as non-disaster include metaphorical context, focusing on the metaphorical tweets and their interaction with large language models such as BERT, RoBERTa and DistilBERT. These experiments showed an improvement compared with the state-of-the-art approaches, demonstrating that these models capture proper metaphorical text representations.
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
Notes
- 1.
Figurative: Said in a sense: That it does not correspond to the literal of a word or expression, but is related to it by an association of ideas. https://dictionary.cambridge.org/es/diccionario/ingles-espanol/figurative.
References
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing System, pp. 6000–6010 (2017)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)
Soriano, C.: La metáfora conceptual. In: Ibarretxe-Antuñano, I., Valenzuela, J. (eds.) Lingüística Cognitiva, pp. 97–121, Anthropos, Barcelona (2012)
Lakoff, G., Johnson, M.: Metaphors We Live By. Chicago University Press, Chicago (1980)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics (2019)
Morales, B.C.: Teoría de la metáfora conceptual y teoría de la metáfora deliberada: propuestas complementarias. Estudios de Lingüística Aplicada 68, 165–198 (2018)
Grady, J., Taub, S., Morgan, P.: Primitive and compound metaphors. In: Goldberg, A.E. (ed.) Conceptual Structure, Discourse and Language, pp. 177–187. Center for the Study of Language and Information, Stanford (1996)
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)
Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)
Parilla-Ferrer, B.E., Fernández, P.L., Ballena, J.T.: Automatic Classification of Disaster-Related Tweets (2015)
Chanda, A.K.: Efficacy of BERT embeddings on predicting disaster from Twitter data. arXiv.org (2021). https://arxiv.org/abs/2108.10698
Song, G., Huang, D.: A sentiment-aware contextual model for real-time disaster prediction using twitter data. Future Internet 13(7), 163 (2021). https://doi.org/10.3390/fi13070163
Saji, B.: Disaster Tweet Classification Using LSTM - NLP. Analytics Vidhya (2022). https://www.analyticsvidhya.com/blog/2022/05/disaster-tweet-classification-using-lstm-nlp/
wisdomml. Disaster Tweets Classification Using Machine Learning & NLP Approach - Wisdom ML. Wisdom ML (2022). https://wisdomml.in/disaster-tweets-classification-using-machine-learning-nlp-approach/
Natural Language Processing with Disaster Tweets Stepanenko, Viktor. Disaster Tweets [Dataset] (2021). https://www.kaggle.com/datasets/vstepanenko/disaster-tweets
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Alcántara, T., García-Vázquez, O., Calvo, H., Torres-León, J.A. (2024). Disaster Tweets: Analysis from the Metaphor Perspective and Classification Using LLM’s. In: Calvo, H., Martínez-Villaseñor, L., Ponce, H. (eds) Advances in Soft Computing. MICAI 2023. Lecture Notes in Computer Science(), vol 14392. Springer, Cham. https://doi.org/10.1007/978-3-031-47640-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-47640-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47639-6
Online ISBN: 978-3-031-47640-2
eBook Packages: Computer ScienceComputer Science (R0)