Analyzing Crowd-Sourced Information and Social Media for Crisis Management

Abstract

The analysis of potentially large volumes of crowd-sourced and social media data is central to meeting the requirements of the Athena project. Here, we discuss the various stages of the pipeline process we have developed, including acquisition of the data, analysis, aggregation, filtering and structuring. We highlight the challenges involved when working with unstructured, noisy data from sources such as Twitter, and describe the crisis taxonomies that have been developed to support the tasks and enable concept extraction. State of the art technology such as formal concept analysis and machine learning is used to create a range of capabilities including concept drill down, sentiment analysis, credibility assessment and assignment of priority. We present an evaluation of results obtained from a set of tweets which emerged from the Colorado wild fires of 2012.

An integrated information lifecycle management framework for exploiting social network data to identify dynamic large crowd concentration events in smart cities applications

“…This may be applied as a next step to the work in this paper (after large crowd concentration and in order to identify what type of crowd this is). The same approach on sentiment analysis through categories and classification, as well as evaluation of credibility for Twitter data is included in [39]. [42] initially investigates and finds a correlation between passenger flows in subway stations and social media posts, in an attempt to predict these flows through the metro system.…”

Organised crime and social media: a system for detecting, corroborating and visualising weak signals of organised crime online

“…Nevertheless, if a predictive element was to be added to the ePOOLICE system, clearly a machine learning approach would be appropriate. Indeed, in a similar, parallel, European project (project ATHENA [34], in which the authors' organisation was a partner), machine learning was added as a means of assessing the credibility of information in social media [35].…”

Twitter-Based Safety Confirmation System for Disaster Situations

“…Recently, social media have played an important information-sharing role during disaster and crisis events [1][2][3]. In particular, the social media application Twitter has gained traction in disaster situations [4][5][6][7][8][9][10][11][12]. On Twitter, users can post pictures and short messages (tweets) in 280 characters (140 Japanese characters) or less.…”