Natural Language Processing for Analyzing Disaster Recovery Trends Expressed in Large Text Corpora

We are developing a new natural language processing (NLP) method to facilitate analysis of text corpora that describe long-term recovery. The aim of the method is to allow users to measure the degree that user-specified propositions about potential issues are embodied within the corpora, serving as a proxy for the disaster recovery process. The presented method employs a statistical syntax-based semantic matching model and was trained on a standard, publicly available training dataset. We applied the NLP method to a news story corpus that describes the recovery of Christchurch, New Zealand after the 2010–2011 Canterbury earthquake sequence. We used the model to compute semantic measurements of multiple potential recovery issues as expressed in the Christchurch news corpus that span 2011 to 2016. We evaluated method outputs through a user study involving twenty professional emergency managers. User study results show that the model can be effective when applied to a disaster-related news corpus. 85% of study participants were interested in a way to measure recovery issue propositions in news or other corpora. We are encouraged by the potential for future applications of our NLP method for after-action learning, recovery decision making, and disaster research.

[1]  Scott B. Miles,et al.  Foundations of community disaster resilience: well-being, identity, services, and capitals , 2015, Environmental Hazards and Resilience.

[2]  Brendan T. O'Connor,et al.  Computational Text Analysis for Social Science: Model Assumptions and Complexity , 2011 .

[3]  Ilan Noy,et al.  What Happened to Kobe? A Reassessment of the Impact of the 1995 Earthquake in Japan , 2012, Economic Development and Cultural Change.

[4]  Hal Daumé,et al.  Deep Unordered Composition Rivals Syntactic Methods for Text Classification , 2015, ACL.

[5]  Brendan T. O'Connor,et al.  Learning to Extract International Relations from Political Context , 2013, ACL.

[6]  David Johnston,et al.  Monitoring wellbeing during recovery from the 2010–2011 Canterbury earthquakes: The CERA wellbeing survey , 2015 .

[7]  Yu-Ru Lin,et al.  The ripple of fear, sympathy and solidarity during the Boston bombings , 2014, EPJ Data Science.

[8]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

[9]  Brendan T. O'Connor,et al.  From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series , 2010, ICWSM.

[10]  Stephanie E. Chang,et al.  Empirical Framework for Characterizing Infrastructure Failure Interdependencies , 2007 .

[11]  Erica Seville,et al.  Urban Disaster Recovery in Christchurch: The Central Business District Cordon and Other Critical Decisions , 2014 .

[12]  Stephanie E. Chang,et al.  Modeling Community Recovery from Earthquakes , 2006 .

[13]  Benjamin Adams,et al.  Identifying salient topics for personalized place similarity , 2014 .

[14]  J. Pennebaker,et al.  Linguistic Markers of Psychological Change Surrounding September 11, 2001 , 2004, Psychological science.

[15]  Stephanie E. Chang,et al.  Urban disaster recovery: a measurement framework and its application to the 1995 Kobe earthquake. , 2010, Disasters.

[16]  Klaus Krippendorff,et al.  Content Analysis: An Introduction to Its Methodology , 1980 .

[17]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[18]  Noah A. Smith,et al.  Semantic Matching Against a Corpus: New Applications and Methods , 2018, ArXiv.

[19]  Noah A. Smith,et al.  Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions , 2010, NAACL.

[20]  James W. Pennebaker,et al.  Cross-Cultural Constructions of Self-Schemas , 2012 .

[21]  Stephanie E. Chang,et al.  Toward Disaster‐Resilient Cities: Characterizing Resilience of Infrastructure Systems with Expert Judgments , 2014, Risk analysis : an official publication of the Society for Risk Analysis.

[22]  Kevin Gimpel,et al.  Towards Universal Paraphrastic Sentence Embeddings , 2015, ICLR.

[23]  Joseph Ashmore,et al.  The Meaning of Build Back Better: Evidence from Post-Tsunami Aceh and Sri Lanka , 2008 .