| Peer-Reviewed

Development of a Disaster Safety Sentiment Index via Social Media Mining

Received: 7 March 2019     Accepted: 28 April 2019     Published: 23 May 2019
Views:       Downloads:
Abstract

People use social media platforms such as Twitter to record their personal thoughts and opinions. Social media platforms reflect people’s sentiments as they are, and an accurate understanding of sentiments on social media could be useful and significant for disaster management. In this research, sentiment type modeling and sentiment quantification are proposed to understand the sentiments presented on social media platforms. Sentiment types are primarily analyzed based on the three major sentiments of affirmation, caution, and observation. Then, for a detailed understanding of sentiment progress according to the progress of a disaster or accident and the government’s response, negative sentiments are categorized into anxiety, disappointment, depression, sadness, and displeasure to enhance the analysis, while positive sentiments are categorized into pleasure, happiness, and relief; Russell’s circumplex model is used to develop a model of eight primary sentiments to acquire an overall understanding of the public’s sentiments. Then, the sentiment index of each sentiment is quantified. Based on the results, the overall sentiment status of the public is monitored, and in the event of a disaster, the public’s sentiment fluctuation rate can be quantitatively observed. Moreover, the influence of disasters and accidents on public sentiments, or the sentiment indices of different accidents, can be compared to identify the accidents that affect public sentiment and public needs after a disaster, and the insights can be used for policy-making.

Published in Journal of Public Policy and Administration (Volume 3, Issue 1)
DOI 10.11648/j.jppa.20190301.14
Page(s) 29-38
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Big Data, Disaster Management, Emotion Analysis, Social Media

References
[1] Jeon Y. S., Kim Y. S., & Jeong S. Y. (1995). Management. Gyeonggi-do: Bobmunsa.
[2] Miller, J. (2012). Psychosocial Capacity Building in Response to Disasters, New York: Columbia University Press.
[3] National Disaster Management Research Institute. (2015). Development of social media utilization guideline for disaster management and enlargement of analysis resources. Final report. Seoul: NDMI.
[4] Choi, S. H., Lee, J. G., & Yeo W. G. (2014). Disaster management competence reinforcement for self-governing bodies using big data. Local Administration Monthly Magazine, 730, 16–19.
[5] Liu, B. (2008). Opinion mining & summarization-sentiment analysis. Retrieved from: http://wwwconference.org/www2008/program/program-tutorials-TA6.html.
[6] Sentiment analysis (2019). Retrieved from: http://en.wikipedia.org/wiki/Sentiment_analysis.
[7] Back, B. H., Ha, I. K., & Ahn, B. C. (2014). An extraction method sentiment information from unstructured big data on SNS. Journal of Korea Multimedia Society, 17 (6), 671–680.
[8] Ryu, P. M., Kim, H. J., Kim, H. K., and Park, S. K. (2012). Social media issue detection & monitoring based on deep language analysis techniques. Communications of Korean Institute of Information Scientists and Engineers, 30 (6), 47–58.
[9] Shin, S. M., & Lee, T. S. (2015). A study on sentiment classification for SNS data analysis. Proceedings of Korean Institute of Information Scientists and Engineers Dec 17-19 2015, Pyeongchang: KIISE Press.
[10] Cha, Y. S., Hwang, M. C., & Kim, S. L. (2011). An empirical study on modeling social emotion evoked during social network service. Proceedings of Korean Society of Emotion and Sensibility. Nov 11, 2011. Gyeongju: KSES Press.
[11] National Disaster Management Research Institute. (2014). Development of social big data semantic monitoring technology. Final report. Seoul: NDMI.
[12] Russell, J. A. (1980). A circumplex model of affect. Journal of Personality and Social Psychology, 39 (6), 1161–1178.
[13] The Ministry of Public Safety and Security. The report on the perceived level of safety. (2016). Retrieved from: http://www.mois.go.kr/mpss/board/file/bbs_0000000000000041/8598/FILE_000000000005597/20160920173330107.pdf; jsessionid=X2l7nh3kzHu4R5SAcxFn3fuE.node11.
Cite This Article
  • APA Style

    Seon Hwa Choi. (2019). Development of a Disaster Safety Sentiment Index via Social Media Mining. Journal of Public Policy and Administration, 3(1), 29-38. https://doi.org/10.11648/j.jppa.20190301.14

    Copy | Download

    ACS Style

    Seon Hwa Choi. Development of a Disaster Safety Sentiment Index via Social Media Mining. J. Public Policy Adm. 2019, 3(1), 29-38. doi: 10.11648/j.jppa.20190301.14

    Copy | Download

    AMA Style

    Seon Hwa Choi. Development of a Disaster Safety Sentiment Index via Social Media Mining. J Public Policy Adm. 2019;3(1):29-38. doi: 10.11648/j.jppa.20190301.14

    Copy | Download

  • @article{10.11648/j.jppa.20190301.14,
      author = {Seon Hwa Choi},
      title = {Development of a Disaster Safety Sentiment Index via Social Media Mining},
      journal = {Journal of Public Policy and Administration},
      volume = {3},
      number = {1},
      pages = {29-38},
      doi = {10.11648/j.jppa.20190301.14},
      url = {https://doi.org/10.11648/j.jppa.20190301.14},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.jppa.20190301.14},
      abstract = {People use social media platforms such as Twitter to record their personal thoughts and opinions. Social media platforms reflect people’s sentiments as they are, and an accurate understanding of sentiments on social media could be useful and significant for disaster management. In this research, sentiment type modeling and sentiment quantification are proposed to understand the sentiments presented on social media platforms. Sentiment types are primarily analyzed based on the three major sentiments of affirmation, caution, and observation. Then, for a detailed understanding of sentiment progress according to the progress of a disaster or accident and the government’s response, negative sentiments are categorized into anxiety, disappointment, depression, sadness, and displeasure to enhance the analysis, while positive sentiments are categorized into pleasure, happiness, and relief; Russell’s circumplex model is used to develop a model of eight primary sentiments to acquire an overall understanding of the public’s sentiments. Then, the sentiment index of each sentiment is quantified. Based on the results, the overall sentiment status of the public is monitored, and in the event of a disaster, the public’s sentiment fluctuation rate can be quantitatively observed. Moreover, the influence of disasters and accidents on public sentiments, or the sentiment indices of different accidents, can be compared to identify the accidents that affect public sentiment and public needs after a disaster, and the insights can be used for policy-making.},
     year = {2019}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Development of a Disaster Safety Sentiment Index via Social Media Mining
    AU  - Seon Hwa Choi
    Y1  - 2019/05/23
    PY  - 2019
    N1  - https://doi.org/10.11648/j.jppa.20190301.14
    DO  - 10.11648/j.jppa.20190301.14
    T2  - Journal of Public Policy and Administration
    JF  - Journal of Public Policy and Administration
    JO  - Journal of Public Policy and Administration
    SP  - 29
    EP  - 38
    PB  - Science Publishing Group
    SN  - 2640-2696
    UR  - https://doi.org/10.11648/j.jppa.20190301.14
    AB  - People use social media platforms such as Twitter to record their personal thoughts and opinions. Social media platforms reflect people’s sentiments as they are, and an accurate understanding of sentiments on social media could be useful and significant for disaster management. In this research, sentiment type modeling and sentiment quantification are proposed to understand the sentiments presented on social media platforms. Sentiment types are primarily analyzed based on the three major sentiments of affirmation, caution, and observation. Then, for a detailed understanding of sentiment progress according to the progress of a disaster or accident and the government’s response, negative sentiments are categorized into anxiety, disappointment, depression, sadness, and displeasure to enhance the analysis, while positive sentiments are categorized into pleasure, happiness, and relief; Russell’s circumplex model is used to develop a model of eight primary sentiments to acquire an overall understanding of the public’s sentiments. Then, the sentiment index of each sentiment is quantified. Based on the results, the overall sentiment status of the public is monitored, and in the event of a disaster, the public’s sentiment fluctuation rate can be quantitatively observed. Moreover, the influence of disasters and accidents on public sentiments, or the sentiment indices of different accidents, can be compared to identify the accidents that affect public sentiment and public needs after a disaster, and the insights can be used for policy-making.
    VL  - 3
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Earthquake Hazard Reduction Center, National Disaster Management Research Institute, Ulsan, Korea

  • Sections