Crisis Response Coordination in Online Communities Whom to coordinate with, Why to coordinate and How to coordinate Motivation • During recent crises, citizens (sensors) are increasingly using social media to share variety of information- situation on the ground, emerging needs, donation offers, damage, etc. • In such a dynamic community, how to extract actionable nuggets from the social media streams to aid relief efforts? Hemant Purohit (advisor: Prof. Amit Sheth) Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis), Wright State University, USA a. Coordination here means managing the competitive intentional behaviors (e.g. needs, offers) b. Psycholinguistic cues help to filter messages with higher information gain for coordination [1] c. Domain dependent analysis helps to understand the context of intentional behavior and therefore, organize information in semantically rich data inventories [2] d. Contextual queries (needs against offers, vice-versa) across space and time help to generate recommendations for both responders as well as informal social community actors [2,3,5] e. Interactive engagement interface with spatio-temporal-thematic and people-content-network analyses allows coordinators to prioritize what to focus and whom to engage with [2,4,5] Application: This framework can be applied to coordinate information seekers vs. helpful knowledgeable users and lurkers in domain-specific forum communities (e.g., Diabetes disease) Approach Highlights Sponsored in part by NSF Grant#IIS-1111182, ‘SOCS: Social Media Enhanced Organizational Sensemaking in Emergency Response’ Second-costliest hurricane in U.S. history estimated damage $75 B 750,000 without power (NY) Hurricane Sandy 2012 285 people killed on the track of Sandy 20+ Million tweets in first week for #Sandy Social Media will aid the existing relief workflows, rather than replace! RT @OpOKRelief: Southgate Baptist Church on 4th Street in Moore has food, water, clothes, diapers, toys, and more. If you can't go,call 794 Text \"FOOD\" to 32333, REDCROSS to 90999, or STORM to 80888 to donate $10 in storm relief. #moore #oklahoma #disasterrelief #donate Want to help animals in #Oklahoma? @ASPCA tells how you can help: http://t.co/mt8l9PwzmO CITIZEN SENSORS RESPONSE TEAMS (including humanitarian org. and ‘pseudo’ responders) Coordination of needs and offers between seekers, suppliers and intermediate responders via automatic analysis Does anyone know where to send a check to donate to the tornado victims? Where do I go to help out for volunteer work around Moore? Anyone know? Anyone know where to donate to help the animals from the Oklahoma disaster? #oklahoma #dogs Matched Matched Matched Serving the need! If you would like to volunteer today, help is desperately needed in Shawnee. Call 273- 5331 for more info VICTIM SITE A big challenge is the very small signal to noise ratio! How to transform the micro- level (tweets) signals into actionable nuggets for macro- level analysis (coordination)? Oklahoma Tornado 2013 one of the deadliest tornadoes in U.S. history killing more than 50 people including 20+ children Approximately 10+ Million tweets in 48 hrs. Coordination Analysis Framework References: 1. H. Purohit, A. Hampton, V. Shalin, A. Sheth, J. Flach, S. Bhatt. What Kind of #Communication is Twitter? Mining #Psycholinguistic Cues for Emergency Coordination. Computers in Human Behavior (CHB) journal, 2013. (To appear) 2. H. Purohit, A. Hampton, S. Bhatt, V. Shalin, A. Sheth, J. Flach. An Information Filtering and Management Model for Twitter Traffic to Assist Crises Response Coordination. Technical Report, Kno.e.sis Center, 2013. (Under Review) 3. H. Purohit, A. Hampton, V. Shalin, A. Sheth, J. Flach. Framework to Analyze Coordination in Crisis Response. Collaboration and Crisis Informatics, Workshop in conjunction with CSCW-2012. 4. H. Purohit and A. Sheth. Twitris v3: From Citizen Sensing to Analysis, Coordination and Action. ICWSM 2013, Demo track. (To appear) 5. A. Sheth, A. Jadhav, P. Kapanipathi, C. Lu, H. Purohit, G. A. Smith, W. Wang. Twitris- a System for Collective Social Intelligence. Encyclopedia of Social Network Analysis and Mining (ESNAM), 2013. *In Progress [1] [2] [2] [2,4,5] [2,3,5]
Leveraging Social Media Communities for Crisis Response Coordination
May 07, 2015
This is a summarized view of doctoral consortium presentation done at NSF SoCS 2013 PI meeting.
During recent crises, citizens (sensors) are increasingly using social media to share variety of information- situation on the ground, emerging needs, donation offers, damage, etc. In such an evolving ad-hoc community, how can we extract actionable nuggets from the social media streams to aid relief efforts? This doctoral consortium presentation summarized in a poster shows a framework to analyze social media data and manage information to assist coordination by focusing on three important questions to answer: Whom to coordinate with, Why to coordinate and How to coordinate. It shows exemplary insights for needs and availability from the recent disaster events.
Check this ICWSM-2013 tutorial partly based on Hemant Purohit's PhD work with his mentors (Dr. Patrick Meier and Dr. Carlos Castillo) and adviser (Prof. Amit Sheth): http://www.slideshare.net/knoesis/icwsm-2013-tutorial-crisis-mapping-citizen-sensing-and-social-media-analytics (details: http://www.knoesis.org/hemant/present/icwsm2013)
Check out the NSF SoCS project on leveraging social media for crisis response: http://knoesis.org/research/semsoc/projects/socs
During recent crises, citizens (sensors) are increasingly using social media to share variety of information- situation on the ground, emerging needs, donation offers, damage, etc. In such an evolving ad-hoc community, how can we extract actionable nuggets from the social media streams to aid relief efforts? This doctoral consortium presentation summarized in a poster shows a framework to analyze social media data and manage information to assist coordination by focusing on three important questions to answer: Whom to coordinate with, Why to coordinate and How to coordinate. It shows exemplary insights for needs and availability from the recent disaster events.
Check this ICWSM-2013 tutorial partly based on Hemant Purohit's PhD work with his mentors (Dr. Patrick Meier and Dr. Carlos Castillo) and adviser (Prof. Amit Sheth): http://www.slideshare.net/knoesis/icwsm-2013-tutorial-crisis-mapping-citizen-sensing-and-social-media-analytics (details: http://www.knoesis.org/hemant/present/icwsm2013)
Check out the NSF SoCS project on leveraging social media for crisis response: http://knoesis.org/research/semsoc/projects/socs
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Crisis Response Coordination in Online CommunitiesWhom to coordinate with, Why to coordinate and How to coordinate
Motivation
• During recent crises, citizens (sensors) are increasingly usingsocial media to share variety of information- situation on theground, emerging needs, donation offers, damage, etc.
• In such a dynamic community, how to extract actionablenuggets from the social media streams to aid relief efforts?
Hemant Purohit (advisor: Prof. Amit Sheth)Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis), Wright State University, USA
a. Coordination here means managing the competitive intentional behaviors (e.g. needs, offers)b. Psycholinguistic cues help to filter messages with higher information gain for coordination [1]c. Domain dependent analysis helps to understand the context of intentional behavior and
therefore, organize information in semantically rich data inventories [2]d. Contextual queries (needs against offers, vice-versa) across space and time help to generate
recommendations for both responders as well as informal social community actors [2,3,5]e. Interactive engagement interface with spatio-temporal-thematic and people-content-network
analyses allows coordinators to prioritize what to focus and whom to engage with [2,4,5]Application: This framework can be applied to coordinate information seekers vs. helpfulknowledgeable users and lurkers in domain-specific forum communities (e.g., Diabetes disease)
Approach Highlights
Sponsored in part by NSF Grant#IIS-1111182, ‘SOCS: Social Media Enhanced Organizational Sensemaking in Emergency Response’
Second-costliest hurricane in U.S. history estimated damage $75 B
750,000 without power (NY)
Hurricane Sandy 2012
285 people killed onthe track of Sandy
20+ Million tweets in first week for #Sandy
Social Media will aid the existing relief workflows, rather than replace!
RT @OpOKRelief: Southgate Baptist
Church on 4th Street in Moore has food, water, clothes, diapers, toys, and more. If you can't
go,call 794
Text \"FOOD\" to 32333, REDCROSS
to 90999, or STORM to 80888 to
donate $10 in storm relief.
#moore #oklahoma#disasterrelief
#donate
Want to help animals in #Oklahoma? @ASPCA tells
how you can help: http://t.co/mt8l9PwzmO
CITIZEN SENSORS
RESPONSE TEAMS (including humanitarian
org. and ‘pseudo’ responders)
Coordination of needs and offers between seekers,
suppliers and intermediate responders
via automatic analysisDoes anyone know
where to send a check to donate to the tornado victims?
Where do I go to help out for volunteer work
around Moore? Anyone know?
Anyone know where to donate to help the animals
from the Oklahoma disaster? #oklahoma #dogs
Matched
Matched
MatchedServing the need!
If you would like to volunteer today, help is desperately needed in
Shawnee. Call 273-5331 for more infoVICTIM SITE
A big challenge is the very small signal to
noise ratio!How to transform the micro-
level (tweets) signals into actionable nuggets for macro-level analysis (coordination)?
Oklahoma Tornado 2013
one of the deadliesttornadoes in U.S. historykilling more than 50 peopleincluding 20+ children
Approximately 10+ Million
tweets in 48 hrs.
Coordination Analysis Framework
References:
1. H. Purohit, A. Hampton, V. Shalin, A. Sheth, J. Flach, S. Bhatt. What Kind of #Communication is Twitter? Mining #Psycholinguistic Cues for Emergency Coordination. Computers in Human Behavior (CHB) journal,2013. (To appear)
2. H. Purohit, A. Hampton, S. Bhatt, V. Shalin, A. Sheth, J. Flach. An Information Filtering and Management Model for Twitter Traffic to Assist Crises Response Coordination. Technical Report, Kno.e.sis Center, 2013.(Under Review)
3. H. Purohit, A. Hampton, V. Shalin, A. Sheth, J. Flach. Framework to Analyze Coordination in Crisis Response. Collaboration and Crisis Informatics, Workshop in conjunction with CSCW-2012.4. H. Purohit and A. Sheth. Twitris v3: From Citizen Sensing to Analysis, Coordination and Action. ICWSM 2013, Demo track. (To appear)5. A. Sheth, A. Jadhav, P. Kapanipathi, C. Lu, H. Purohit, G. A. Smith, W. Wang. Twitris- a System for Collective Social Intelligence. Encyclopedia of Social Network Analysis and Mining (ESNAM), 2013.
*In Progress
[1]
[2]
[2]
[2,4,5]
[2,3,5]
Related Documents
