Summary about Social Media Research in Disaster/Emergency Response Systems

From Knoesis wiki
Revision as of 22:15, 17 November 2011 by Hemant (Talk | contribs) (Related Project)

Jump to: navigation, search

Related Project

SoCS: Social Media Enhanced Organizational Sensemaking in Emergency Response

Keywords: Social Networking, Emergency Response, Content Analysis, Network Analysis, Organizational Sensemaking, Collaborative Decision Making.

PI/PM: Amit Sheth

Co-PIs: Valerie Shalin, John Flach (Department of Psychology, Human Factors/Industrial Organization Graduate Program)

Collaborator and OSU PI: Srinivasan Parthasarthy, Ohio State University

Funding: This research is funded by the National Science Foundation under award IIS-1111182, 09/01/2011 - 08/31/2014.

Students: Hemant Purohit, Andrew Hampton,Yiye Ruan

See also: Twitris: The Social Brain, Semantics driven Analysis of Social Media, Citizen Sensing, Social Signals, and Enriching Human Experience, Computing For Human Experience

In News:



Here are the summaries for articles posted in news/blogs about research in Disaster/Emergency Response Systems. We keep updating these summaries, please check out again.

Tweak-the-tweet

This project seeks to build a collaboration network to promote Tweet-friendly hashtag-based syntax to help direct Twitter communications for more efficient data extraction for those communicating about the Haiti earthquake disaster. It modifies tweet pieces dependent on subject to make them more easily machine-parsable. The syntax is constantly evolving. Each tweet counted must have #haiti and only one other key word (need, offering, ruok, trapped, etc.)

Example:

TWEET-BEFORE: Altagrace Pierre needs help at Delmas 14 House no. 14.

TWEET-AFTER: #haiti #name Altagrace Pierre #need help #loc Delmas 14 House no. 14.

Source: http://wiki.crisiscommons.org/wiki/Tweak_the_Tweet

Dated: Oct 1, 2011

Truthy Project

This project focuses on shared traits of information diffusion via social media sites. They hope to offer real-time analysis of data encompassing millions of posts daily. It will model the data stream as “a series of time-stamped events that represent interactions between actors and memes.” Mood tracking methods cross-validated against stocks, weather and news will be used for meme characterization. This data would let them deduce why certain memes catch on and others don’t.

Source: http://newsinfo.iu.edu/news/page/normal/19178.html

Dated: Nov 9, 2011

Social Media and Disasters

This report focuses on the government’s efforts to use various social media to better manage emergencies by informing citizens of potential danger and allowing communication from citizens to allow for two-way information flow. Very little technical information is given.

Sources: http://www.fas.org/blog/secrecy/2011/09/social_media.html http://www.fas.org/sgp/crs/homesec/R41987.pdf

Dated: Nov 9, 2011

eMoksha Projects

Encompasses many smaller projects: VoteReport India- citizen-powered monitoring to track election irregularities during general elections FixOurCity- promotes citizen participation in government Kiirti- platform to allow government, non-government and civic organizations to communicate with citizens through phone, sms, email and web. iDemocracy Camp- “unconference” promoting citizen engagement in government for a day of intense collaboration Sharek961.org- allows Lebanese to send in eyewitness reports of election-related issues/incidents (sms, email or web) Alive in Afghanistan- citizens directly report on their political process Sudan Vote Monitor- effort to increase transparency in elections

Source: http://emoksha.org/projects.html

Dated: Nov 9, 2011

Ushahidi use-case

During a bombing in Mumbai, phone lines were clogged so people turned to social media for coordination and discussion. A Google Docs spreadsheet was created (hundreds of miles away) that allowed communication for people to volunteer their homes for those who needed refuge. Also, a disaster tracker map was used to identify salient locations (shelters, stranded people, etc.) Time-relevance of the information was manually evaluated by time stamp. Very little automation used in any of these outside of publicly available software applications.

Source: http://www.economist.com/blogs/babbage/2011/07/online-crisis-management

Dated: Nov 9, 2011

Decoding our Chatter

Want to monitor an earthquake, track political activity or predict the ups and downs of the stock market? Researchers have found a bonanza of real-time data in the torrential flow of Twitter feeds.

Source: http://online.wsj.com/article/SB10001424052970204138204576598942105167646.html

Dated: Nov 9, 2011

Twitcident

This graphic software allows for filtered searching on a large corpus of tweets. It also provides analytics that let users get an overview and analyze what is being reported about an incident in the social web stream. Information relevant to a particular incident is automatically filtered and sorted for easy reference. The data is continuously reevaluated to create a real time profile of the incident. This is accomplished by first aggregating social media data, then applying semantic techniques such as classification, linkage, and metadata extraction, and lastly filtering patterns that emerge to provide usable and searchable data, which in turn feed back in to the incident profile.

Source: http://wis.ewi.tudelft.nl/twitcident/

Dated: Nov 10, 2011