Spatial Text Mining: An Enhanced Text-Mining Framework for Disaster Relevant Social Media Data Classification

Authors: Qunying Huang*, University of Wisconsin - Madison, Christopher Scheele, UW-Madison
Topics: Cyberinfrastructure, Geographic Information Science and Systems, Hazards, Risks, and Disasters
Keywords: text mining, machine learning, data mining, social media
Session Type: Paper
Day: 4/13/2018
Start / End Time: 5:20 PM / 7:00 PM
Room: Napoleon D1, Sheraton 3rd Floor
Presentation File: No File Uploaded

To find disaster relevant social media data and automatically categorize them into different classes (e.g. damage or donation), current approaches utilize natural language processing (NLP) methods based on keywords, or machine learning algorithms relying on text only. However, these classification approaches have not been perfected due to the variability and uncertainty in language used on social media. A disaster relevant social media post is highly sensitive to the location and time of the post. Thus, additional features related to space and time could be useful for differentiating relevant posts. This study proposed a spatial text mining framework to incorporate spatial information derived from social media and authoritative meteorological datasets, along with the text information, for classifying disaster relevant social media posts. An assessment of the framework utilized geo-tagged social media posts and meteorological data for the 2012 Hurricane Sandy disaster event. Commonly used machine learning algorithms, including Naive Bayes and Support Vector Machine classifiers, tested and demonstrated the performance improvements of the enhanced text-mining framework. The results from this study address the need for incorporating spatial data when using social media in disaster management applications.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login