Big Data Analysis
Student’s Name
Institutional affiliation
Course
Professor’s Name
Date
Social Media Big Data Analysis for Disaster Management: A Systematic Review
Paper Summary
A systematic review of social media big data for Disaster Management (DM).Social media big data facilitates back channels of information through data sensing. This paper aims at the peculiarities of data sensing, including gaps, challenges that define effectiveness. The findings were drawn from scholarly articles. Time is critical in DM. Rapid onset disasters require situational awareness. Traditional methods, such as field surveying and remote sensing, cannot achieve situational awareness. Social media has been vibrant in facilitating wide-scale interaction, including warning travelers on impending danger as Google maps, which notifies drivers on jam-infested roads.
The paper employed the following methods in scrutinizing literature;
- Network analysis
- Bibliometric
- Reviewing of lit
- Classifying sources
Findings prove that Studies on the effectiveness of social media big data in DM are minimal. Most studies relate to computer science and Eng. To add on, reviews on the topic increased as of 2015. Studies that employed concept, survey, experiment, case studies met the criterion for a conceptual framework. The effectiveness of social media big data on DM depends on the mentioned criterion. Fewer studies focused on Data analysis, experimentation, and data analysis of factors that contribute to social media’s effectiveness and efficiency of big data on DM. The paper recommends the need for studies on areas that are yet to be explored.
Abstract
The world is currently experiencing an era of big data analytics that can revolutionize disaster management (DM). Big data analytics allows experts to visualize, conduct analysis, and predict impending disaster, vital for crisis management and humanitarian operations. Social media Big Data is creating a backchannel that can detect emergencies through wide-scale interactions. The backchannel communication is resourceful for self-policing and creates an opportunity for experts to gather the information that would have been tough or expensive to collect. The potentiality of big data is attracting many researchers, and yet most literature remains diverse and fragmented. This paper embarks on a systematic review to narrow down on the peculiarities of social media big data on DM; this includes relevant contributions, challenges, gaps, and recommendations for future studies. The findings were drawn for scholarly journals and papers that had been cited mostly based on yearly dues. Results prove academic work that is based on DM context following classifications of publications and analyzing trends.
Keywords: Social Media, Big Data, Twitter, Facebook, Real-time disaster management, Data sensing
Background
Disaster management requires relevant information to be gathered expertly. Traditional methods such as filed surveying and remote sensing to collect data prove futile, especially with regards to time. Time is critical in Disaster management since acquiring substantial information promptly helps inadequate planning and prompt reaction. Rapid onset disasters require situational awareness to help in real-time disaster management (Li et al., 2019). Social media has been vibrant in facilitating wide-scale interaction, including warning travelers on impending danger. As seen in Google maps, the backchannel communication warns road users on roads that jam prevalent are proving useful for crisis management. According to Choi and Bae (2015), Facebook and Twitter have allowed an infinite utilization potential for accurate, intelligent, and promptness in Disaster management.
Methodology
While Data sensing through social media’s backchannel communication is proving imperative for DM, the field studies are yet to attain maturity. Fewer studies have been made to explore challenges and gaps in suing social media data sense to achieve the efficacy of its usage. This paper employs network analysis and bibliometric to scout and establish critical literature that informs the knowledge of data sensing with a particular focus on the gaps and challenges. In doing so, the paper will be able to recommend areas that need future studies. To achieve a reliable scope for the comprehensive literature, the research objective encompassed the following 4-stage protocol.
- A search of sources that inform the contextual framework; 25 sources were gathered.
- Using the conceptual framework to analyses and classify the most relevant articles, five sources were retained.
- An in-depth analysis of the articles to obtain commonness and disparities of findings
- Establishing areas that need future studies
Searching and classifying sources
To settle on studies that possess the most significant impact on the effectiveness of social media big data for DM, the paper reviewed 25 studies. The 25 initial studies mentioned big data in the context of social media usage. Most of them ranged from 2005 to 2019. The sources were obtained using a grey literature search on Google scholar and relevant recommended studies. Empirical studies that reported on big data analysis, social media information dissemination and the effectiveness of big data analytics on DM were also included. Obtained literature was analyzed based on topic coherence, where studies that explored the relevancy of social media big data in managing disasters were selected. While most studies contributed to social media big data in DM, a handful evaluated its effectiveness regarding challenges, gaps, and extend of usage. Findings prove that the topic of big data and DM had been explored more between 2016 to 2018, especially in the fields of engineering and computer science, as shown in the below.
Graph showing topic coverage based on subject areas.
Graph showing the prevalence of studies based on years.
Findings: Review of Results-Based On Conceptual Framework
Five studies depicted many similarities in the comprehensive coverage of the effectiveness of social media big data for DM. Works by Li et al. (2019), Chois and Bae,(2015), Athanasis et al. ( 2018), Albuquerque et al., (2015), and Shibuya (2017) provided comprehensive information on how social media was achieving success through backflow information channels that provided attention on arrears that experienced disasters. Works by Choi and Bae(2015) and Albuquerque et al. (2015) explored the effectiveness of social media in providing real-time or contextual assistance for data sensing. In relation, the other authors examined why social media big data was proving imperative for disaster management with a particular focus on relevant metrics. According to Wamba et al. (2015), parameters that make social media big data as a viable tool for DM include conceptual efficacy, surveying instrumentation, experimental analysis, case studies, Data analysis, and Reviewing for authenticity. The metrics determine how reliable backchannel information can achieve effectiveness as appropriate directories (Wamba et al., 2015). Other relevant sources on basis approach metrics and contributions are summarized in the table below.
| Approach | References | Relevancy (%) |
| conceptual | (Li et al. 2019), (Chois and Bae, 2015), (Athanasis et al., 2018), (Albuquerque et al., 2015), (Shibuya 2017), (Wamba et al., 2015) (Waugh, 2000), (Wang et al., 2016), (Ji-fan Ren et al., 2017), (Jianping et al., 2016), (Jean-Pierre, 2013), (Janke, 2016), (Jahre,2007), (Gao et al., 2011), (Galindo, 2013), (Cinnamon et al., 2016) (Cherichi, 2016),
|
33% |
| Survey | (Chang, 2016) (Li et al. 2019), (Chois and Bae, 2015), (Athanasis et al., 2018), (Albuquerque et al., 2015), (Shibuya 2017), (Wamba et al., 2015) | 20% |
| Experiments | (Gelenter & Mushegian, 2011), (Chois and Bae, 2015), (Albuquerque et al., 2015), | 5% |
| Case studies | (Chung & Park, 2016) (Albuquerque et al., 2015), (Shibuya 2017), (Wamba et al., 2015) | 10% |
| Data analysis | (Li et al. 2019)(Chois and Bae, 2015) | 1% |
| Review | (Gamal, 2010) (Albuquerque et al., 2015), (Shibuya 2017), (Wamba et al., 2015) (Waugh, 2000), (Wang et al., 2016), (Ji-fan Ren et al., 2017), (Jianping et al., 2016), (Jean-Pierre, 2013), (Janke, 2016), (Jahre,2007), (Gao et al., 2011), (Galindo, 2013), (Cinnamon et al., 2016) (Cherichi, 2016), | 33% |
Conclusions and Recommendations
The efficiency of social media big data in disaster management is based on spreading relevant information to the appropriate authorities or society promptly. The backchannel information should provide contextual information and, if possible, facilitate surveys to allow proper coordination of disaster management. Future studies need to explore challenges affecting the back channels of information with a particular focus on data analysis, and experimentations to identify problems and gaps affecting social media big data for Disaster management.
References
Athanasis, N., Themistocleous, M., Kalabokidis, K., Papakonstantinou, A., Soulakellis, N., & Palaiologou, P. (2018). The Emergence Of Social Media For Natural Disasters Management: A Big Data Perspective. ISPRS – International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3/W4, 75-82. doi:10.5194/isprs-archives-xlii-3-w4-75-2018
Albuquerque, J. P., Herfort, B., Brenning, A., & Zipf, A. (2015). A geographic approach for combining social media and authoritative data towards identifying useful information for disaster management. International Journal of Geographical Information Science, 29(4), 667-689. doi:10.1080/13658816.2014.996567
Choi, S., & Bae, B. (2015). The Real-Time Monitoring System of Social Big Data for Disaster Management. Computer Science and Its Applications Lecture Notes in Electrical Engineering, 809-815. doi:10.1007/978-3-662-45402-2_115
Chang, C.-I., & Lo, C.-C. (2016). Planning and implementing a smart city in Taiwan. IT Professional,18,42–49.
Chang, V. (2015). Towards a big data system disaster recovery in a private cloud. Ad Hoc Networks,35, 65–82.
Cherichi, S., & Faiz, R. (2016). Upgrading event and pattern detection to big data. In International conference on collective computational intelligence. Springer.
Chung, K., & Park, R. C. (2016). P2P cloud network services for IoT based disaster situations information.Peer-to-Peer Networking and Applications,9(3), 566–577.
Cinnamon, J., Jones, S. K., & Adger, W. N. (2016). Evidence and future potential of mobile phone data for disease disaster management. Geoforum,75, 253–264.
Galindo, G., & Batta, R. (2013). Review of recent developments in OR/MS research in disaster operations
management. European Journal of Operational Research,230, 201–211.
Gamal-Aboelmaged, M. (2010). Six Sigma quality: A structured review and implications for future research. International Journal of Quality & Reliability Management,27(3), 268–317.
Gao, H., Barbier, G., & Goolsby, R. (2011). Harnessing the crowdsourcing power of social media for disaster relief. IEEE Intelligent Systems,26(3), 10–14. Gelernter, J., & Mushegian, N. (2011). Geo-parsing messages from the micro text. Transactions in GIS,15(6),753–773
Jahre, M., Persson, G., Kovács, G., & Spens, K. M. (2007). Humanitarian logistics in disaster relief operations.International Journal of Physical Distribution & Logistics Management,37, 99–114
.Janke, A. T., Overbeek, D. L., Kocher, K. E., & Levy, P. D. (2016). Exploring the potential of predictive analytics and big data in emergency care. Annals of Emergency Medicine,67, 227–236.
Jean-Pierre, D. (2013). Oracle: Big data for the enterprise. Redwood City, CA: Oracle Corporation.
Jianping, C., Jie, X., Qiao, H., Wei, Y., Zili, L., Bin, H., et al. (2016). Quantitative geoscience and geological significant data development: A review. Acta Geologica Sinica (English Edition),90, 1490–1515.
Ji-fan Ren, S., Fosso Wamba, S., Akter, S., Dubey, R., & Childe, S. J. (2017). Modeling quality dynamics, business value, and firm performance in a big data analytics environment. International Journal of Production Research,55(17), 5011–5026.
Li, Z., Huang, Q., & Emrich, C. T. (2019). Introduction to social sensing and big data computing for disaster management. International Journal of Digital Earth, 12(11), 1198-1204. doi:10.1080/17538947.2019.1670951
Shibuya, Y. (2017). Mining social media for disaster management: Leveraging social media data for community recovery. 2017 IEEE International Conference on Big Data (Big Data). doi:10.1109/bigdata.2017.8258286
Wamba, S. F., Akter, S., Edwards, A., Chopin, G., & Gnanzou, D. (2015). How ‘big data’ can make a big impact: Findings from a systematic review and a longitudinal case study. International Journal of Production Economics, 165, 234-246. doi:10.1016/j.ijpe.2014.12.031
Wang, X., Wu, Y., Liang, L., Huang, Z., 2016. Service outsourcing and disaster response methods in the relief supply chain. Annals of Operations Research 240, 471-487.
Wang, Y., Chen, C., Wang, J., and Baldick, R., 2016. Research on the resilience of power systems under natural disasters—A review. IEEE Transactions on Power Systems, 31(2), pp.1604-1613.
Waugh, W.L., Jr., 2000. Living with Hazards, Dealing with Disasters: An Introduction to emergency management. M.E. Sharpe, Armonk, NY.
Wang, Y., Zhang, H., He, D., Guo, C., Zhu, W. and Yang, W. 2016. Function design and system architecture of disaster prevention and dispatch system in power systems based on big data platforms.Dianwang Jishu/Power System Technology, 40 (10), pp. 3213-3219.