9 Understanding Social-Mediated Disaster …
171
More importantly, this study posits the importance of bringing big data tools
to address the complexity of disaster and risk communication. Traditional quantitative units exploring linear relationships and group differences may not effectively describe such chaotic systems (Murphy 1996). To unpack this conundrum,
this chapter presents a case study to demonstrate that integrating topic modeling
with content analysis can better capture the details of disaster and risk communication on social media and identify the public’s concerns and requests. With this
attempt, this chapter hopes to bring a discussion about what new methods can be
adapted to handle the complexity of disaster risk. The knowledge will help researchers
refine disaster risk framework and guide governments and emergency practitioners
to provide effective communication and prompt disaster relief responses.
9.6.2 Future Directions
Disaster risk research faces many challenges because it requires multi-dimensional
cooperation among various disciplines (e.g., public health, emergency management, and disaster risk communication) and different stakeholders (e.g., government,
emergency management institutions, and communities). Although many emergency
management institutions start utilizing social media to deliver messages to the public,
institutional guidance and evidence remain unclear regarding how to take advantage
of social media in preparation for a future crisis, monitor communication on social
media, guide information flow, and respond to the public’s opinions expressed on
social media.
This chapter highlights the value of embracing the public’s opinions in emergency management. The growing technology significantly impacts disaster and risk
communication among emergency management agencies, mass media, and general
citizens. The traditional one-way, top-down communication ignores the public’s
opinions (Jin and O’Hair 2020). In the future, more efforts should be devoted to
examining disaster risk communication among the various stakeholders across platforms, such as governmental agencies’ websites, newspapers, television, and social
media.
Furthermore, this chapter encourages future researchers to utilize machine
learning tools to address disaster risk problems. Machine learning, such as topic
modeling, may be able to help researchers refine disaster risk frameworks. Such
knowledge will provide implications for future theory building in disaster and risk,
as well as practice in emergency management.
9.7 Conclusions
This book chapter highlights the importance of exploring open discussions about
diasters on social media during the resolution period. It also proposes to apply big data
171
More importantly, this study posits the importance of bringing big data tools
to address the complexity of disaster and risk communication. Traditional quantitative units exploring linear relationships and group differences may not effectively describe such chaotic systems (Murphy 1996). To unpack this conundrum,
this chapter presents a case study to demonstrate that integrating topic modeling
with content analysis can better capture the details of disaster and risk communication on social media and identify the public’s concerns and requests. With this
attempt, this chapter hopes to bring a discussion about what new methods can be
adapted to handle the complexity of disaster risk. The knowledge will help researchers
refine disaster risk framework and guide governments and emergency practitioners
to provide effective communication and prompt disaster relief responses.
9.6.2 Future Directions
Disaster risk research faces many challenges because it requires multi-dimensional
cooperation among various disciplines (e.g., public health, emergency management, and disaster risk communication) and different stakeholders (e.g., government,
emergency management institutions, and communities). Although many emergency
management institutions start utilizing social media to deliver messages to the public,
institutional guidance and evidence remain unclear regarding how to take advantage
of social media in preparation for a future crisis, monitor communication on social
media, guide information flow, and respond to the public’s opinions expressed on
social media.
This chapter highlights the value of embracing the public’s opinions in emergency management. The growing technology significantly impacts disaster and risk
communication among emergency management agencies, mass media, and general
citizens. The traditional one-way, top-down communication ignores the public’s
opinions (Jin and O’Hair 2020). In the future, more efforts should be devoted to
examining disaster risk communication among the various stakeholders across platforms, such as governmental agencies’ websites, newspapers, television, and social
media.
Furthermore, this chapter encourages future researchers to utilize machine
learning tools to address disaster risk problems. Machine learning, such as topic
modeling, may be able to help researchers refine disaster risk frameworks. Such
knowledge will provide implications for future theory building in disaster and risk,
as well as practice in emergency management.
9.7 Conclusions
This book chapter highlights the importance of exploring open discussions about
diasters on social media during the resolution period. It also proposes to apply big data