D-record: Disaster Response and Relief Coordination Pipeline

We employ multi-modal data (i.e., unstructured text, gazetteers, and imagery) for location-centric demand/request matching in the context of disaster relief. After classifying the Need expressed in a tweet (the WHAT), we leverage OpenStreetMap to geolocate that Need on a computationally accessible map of the local terrain (the WHERE) populated with location features such as hospitals and housing. Further, our novel use of flood mapping based on satellite images of the affected area supports the elimination of candidate resources that are not accessible by road transportation. The resulting map-based visualization combines disaster-related tweets, imagery and pre-existing knowledge-base resources (gazetteers) to reduce decision-making latency and enhance resiliency by assisting individual decision-makers and first responders for relief effort coordination.

[1]  Amit P. Sheth,et al.  Location Name Extraction from Targeted Text Streams using Gazetteer-based Statistical Language Models , 2017, COLING.

[2]  Amit P. Sheth,et al.  Identifying Seekers and Suppliers in Social Media Communities to Support Crisis Coordination , 2014, Computer Supported Cooperative Work (CSCW).

[3]  Manas Gaur,et al.  Feature Engineering for Twitter-based Applications , 2018 .

[4]  Sarah Vieweg,et al.  Processing Social Media Messages in Mass Emergency , 2014, ACM Comput. Surv..

[5]  Vaninha Vieira,et al.  Visualization mechanisms for crowdsourcing information in emergency coordination , 2015, IHC.

[6]  Irina P. Temnikova,et al.  EMTerms 1.0: A Terminological Resource for Crisis Tweets , 2015, ISCRAM.

[7]  Amit P. Sheth,et al.  A Practical Incremental Learning Framework For Sparse Entity Extraction , 2018, COLING.

[8]  Muhammad Imran,et al.  Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages , 2016, LREC.

[9]  Smriti Murali,et al.  Crowdsourcing for disaster relief: A multi-platform model , 2016, 2016 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER).

[10]  Srinivasan Parthasarathy,et al.  Human-Guided Flood Mapping: From Experts to the Crowd , 2018, WWW.

[11]  Bartel Van de Walle,et al.  Open source software for disaster management , 2007, Commun. ACM.

[12]  Xiao Zhang,et al.  SensePlace2: GeoTwitter analytics support for situational awareness , 2011, 2011 IEEE Conference on Visual Analytics Science and Technology (VAST).

[13]  K. Nagel,et al.  Measuring vulnerability to promote disaster-resilient societies: Conceptual frameworks and definitions , 2006 .

[14]  Hui Wang,et al.  A Knowledge Management and Need-Capacity Matching Approach for Community-Based Disaster Management and Recovery , 2015, 2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE).

[15]  Carlos Castillo,et al.  What to Expect When the Unexpected Happens: Social Media Communications Across Crises , 2015, CSCW.

[16]  Jie Yin,et al.  Emergency situation awareness from twitter for crisis management , 2012, WWW.

[17]  Amit P. Sheth,et al.  Assisting coordination during crisis: a domain ontology based approach to infer resource needs from tweets , 2014, WebSci '14.

[18]  Zhi-Hua Hu,et al.  A container multimodal transportation scheduling approach based on immune affinity model for emergency relief , 2011, Expert Syst. Appl..

[19]  Matthias Moi,et al.  AN ONTOLOGY FOR THE USE OF QUALITY EVALUATED SOCIAL MEDIA DATA IN EMERGENCIES , 2016 .