Abstract
The disaster management is highly responsible for managing the evacuation and deploying rescue teams to reduce the loss of lives and properties. However, it is considered challenging to obtain accurate information in timely fashion from various regions of the affected zones. With the advent of social media and networks, the information dissemination on such events can sense wide information from different zones but the information is in unstructured form. It is hence necessary to acquire correct or relevant information relating to that event. In this paper, we utilize random forest (RF) model to effectively classify the information from tweets (twitter.org) to find the location in case of a natural disaster. The proposed classification engine involves the collects of tweets, pre-processing of texts, RF classification and the extraction of location and determination. The classification is made effective using a pre-trained word vectors that includes the crisis words and global vectors for word representation (GLoVe). This pre-training captures the semantic meaning from the input tweets. Finally, extraction is performed to increase the accuracy of the model and in addition it determines the location of the disaster. The experiments are conducted on a real datasets from recent hurricanes. The results of simulation shows that the RF performs in a better way than other existing models in terms of accuracy, recall, precision and F1-score. It is seen that RF classifies effectively the tweets and analyses the accurate location.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Park, M., Sun, Y., McLaughlin, M.L.: Social media propagation of content promoting risky health behavior. Cyberpsychol. Behav. Soc. Netw. 20(5), 278–285 (2017)
Garimella, K., Morales, G.D.F., Gionis, A., Mathioudakis, M.: Quantifying controversy on social media. ACM Trans. Soc. Comput. 1(1), 1–27 (2018)
Alexander, D.E.: Social media in disaster risk reduction and crisis management. Sci. Eng. Ethics 20(3), 717–733 (2014)
Yang, Z., Nguyen, L.H., Stuve, J., Cao, G., Jin, F.: Harvey flooding rescue in social media. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 2177–2185. IEEE, December 2017
Shklovski, I., Burke, M., Kiesler, S., Kraut, R.: Technology adoption and use in the aftermath of Hurricane Katrina in New Orleans. Am. Behav. Sci. 53(8), 1228–1246 (2010)
Baer, D.: As Sandy became# Sandy, emergency services got social. Fast Company, vol. 9 (2012)
Lindsay, B.R.: Social media and disasters: current uses, future options, and policy considerations (2011)
Ferrara, E., Wang, W.Q., Varol, O., Flammini, A., Galstyan, A.: Predicting Online Extremism, Content Adopters, and Interaction Reciprocity. International Conference on Social Informatics, pp. 22–39. Springer, New York (2016)
Azizan, S.A., Aziz, I.A.: Terrorism detection based on sentiment analysis using machine learning. J. Eng. Appl. Sci. 12(3), 691–698 (2017)
Hartung, M., Klinger, R., Schmidtke, F., Vogel, L.: Identifying right-wing extremism in German Twitter profiles: a classification approach. In: Frasincar, F., Ittoo, A., Nguyen, L.M., Métais, E. (eds.) NLDB 2017. LNCS, vol. 10260, pp. 320–325. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59569-6_40
Nguyen, A., Hoang, Q., Nguyen, H., Nguyen, D., Tran, T.: Evaluating marijuana-related tweets on Twitter. In: IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC), pp. 1–7. IEEE, New Jersey (2017)
Ryan, S., Garth, D., Richard, F.: Searching for signs of extremism on the web: an introduction to sentiment-based identification of radical authors. Behav. Sci. Terror. Polit. Aggres. 10, 39–59 (2018)
Chalothorn, T., Ellman, J.: Using SentiWordNet and sentiment analysis for detecting radical content on web forums (2012)
Bermingham, A., Conway, M., McInerney, L., O’Hare, N., Smeaton, A.F.: Combining social network analysis and sentiment analysis to explore the potential for online radicalisation. In: IEEE International Conference on Advances in Social Network Analysis and Mining, ASONAM 2009. pp. 231–236 (2009)
Zahera, H.M., Jalota, R., Sherif, M.A., Ngomo, A.N.: I-AID: identifying actionable information from disaster-related tweets. arXiv preprint arXiv:2008.13544 (2020)
Garvey, W.T., Mechanick, J.I.: Medically actionable disease classification system for obesity. Obesity (Silver Spring, Md.) 28(7), 1169 (2020)
Garvey, W.T., Mechanick, J.I.: Proposal for a scientifically correct and medically actionable disease classification system (ICD) for obesity. Obesity 28(3), 484–492 (2020)
Tzacheva, A.A., Ranganathan, J., Bagavathi, A.: Action rules for sentiment analysis using Twitter. Int. J. Soc. Netw. Mining 3(1), 35–51 (2020)
Kruspe, A., Kersten, J., Klan, F.: Detection of actionable tweets in crisis events. Nat. Hazard. 21(6), 1825–1845 (2021)
Roy, S.S., Dey, S., Chatterjee, S.: Autocorrelation aided random forest classifier-based bearing fault detection framework. IEEE Sens. J. 20(18), 10792–10800 (2020)
Adams, G., Ketenci, M., Bhave, S., Perotte, A., Elhadad, N.: Zero-shot clinical acronym expansion via latent meaning cells. In: Machine Learning for Health, pp. 12–40. PMLR, November 2020
Miller, M., Romine, W.L.: Anthrax event detection using Twitter: analysis of unigram and bigrams for relevant vs non-relevant tweets (2020)
HaCohen-Kerner, Y., Miller, D., Yigal, Y.: The influence of preprocessing on text classification using a bag-of-words representation. PLoS ONE 15(5), e0232525 (2020)
Duan, Z., et al.: Towards cleaner wastewater treatment for special removal of cationic organic dye pollutants: a case study on application of supramolecular inclusion technology with β-cyclodextrin derivatives. J. Clean. Prod. 256, 120308 (2020)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543, October 2014
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
Kanimozhi, T., Belina V J Sara, S. (2022). Classification of Tweet on Disaster Management Using Random Forest. In: Rajagopal, S., Faruki, P., Popat, K. (eds) Advancements in Smart Computing and Information Security. ASCIS 2022. Communications in Computer and Information Science, vol 1759. Springer, Cham. https://doi.org/10.1007/978-3-031-23092-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-23092-9_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23091-2
Online ISBN: 978-3-031-23092-9
eBook Packages: Computer ScienceComputer Science (R0)