Skip Ribbon Commands
Skip to main content
News
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
2005
2004
2003
2002
 

Humanitarian computing research uses Twitter to prioritize crisis response
6/22/2017
Jennifer Muller  |  Office of Communications  |  media@aub.edu.lb  | 

​​

Natural disasters often happen with little or no advance warning, making it difficult for emergency workers to understand the scale of the crisis and help those affected. Research being done at AUB is taking an innovative approach to this problem and looking at how humanitarian computing can be used in connection with social media to quickly identify and classify natural disasters to help guide the work of first responders.

It is estimated that almost 400 natural disasters—such as earthquakes, wildfires, and hurricanes—occur each year. These disasters cause hundreds of thousands of casualties and material damage valued at more than 150 billion dollars. With more than 3 billion people online, it is no surprise that images from disaster scenes are posted on social media, often as the devastation is unfolding. Professor Mariette Awad and her research team in the Maroun Semaan Faculty of Engineering and Architecture (SFEA) wondered whether these images and text could be put to practical use during a crisis.  

At the 12th International Conference on Signal-Image Technology and Internet-Based Systems in Naples, Italy, Dr. Awad and her students Hadi S. Jomaa and Yara Rizk, reported a new automated approach to rapidly identify disasters and classify them by type. The system is in its early stages of development but it has so far proven to be more than 95% accurate in its ability to categorize damage. 

Dr. Awad and her team are proposing to mine online images and text from Twitter in order to help emergency workers prioritize their response to natural disasters. During crises, first responders are a scarce resource and time is of the essence. This system can help them identify the most urgent needs, such as a building that is about to fall down or a landslide that is about to occur. This research is in the flourishing field of humanitarian computing, which is the use of information technology to better the lives of people.

To create the system, the AUB researchers gathered images tweeted by people during natural disasters and divided them into two broad categories of damage: infrastructure and nature. The system uses colors, shape, texture, and feature combinations to help identify the image category. The research team then developed two “bags of words” to describe the images in each category so that the tweet content is better mapped to the annotated image.

“People say an image is worth a thousand words, so an annotated image is even more powerful,” said Dr. Awad, noting that previous research has focused only on the tweet text whereas they are focusing on both the image and the text of tweets to provide more robust information.   

Dr. Awad is an associate professor in the Department of Electrical and Computer Engineering in SFEA and an expert in machine learning. She explained that “this system can grow and learn, becoming more autonomous and expert based on experience gathered from the social media content.” Professor Awad also pointed out that this system could be utilized in other contexts and hopes that, in the future, humanitarian computing will be used in war zones in order to prioritize the work of first responders and help save lives.
Story Highlights
  • ​Natural disasters often happen with little or no advance warning, making it difficult for emergency workers to understand the scale of the crisis and help those affected. Research being done at AUB is taking an innovative approach to this problem and looking at how humanitarian computing can be used in connection with social media to quickly identify and classify natural disasters to help guide the work of first responders.​
 
Related Info
Contact Info
Office of Communications
Tel: 961-1-350000 Ext. 2670
Email: media@aub.edu.lb
 
 
News AUB in the News
Google Plus AUB Google+ Page
Facebook AUB Facebook Page
You Tube AUB YouTube Channel
Twitter AUB Twitter Page
Instagram AUB Instagram Account
Contact us Jobs Disclaimer Copyright Non-Discrimination/Title IX