The detection and location estimation of disasters using Twitter and the identification of Non-Governmental Organisations using crowdsourcing

This paper provides the humanitarian community with an automated tool that can detect a disaster using tweets posted on Twitter, alongside a portal to identify local and regional Non-Governmental Organisations (NGOs) that are best-positioned to provide support to people adversely affected by a disaster. The proposed disaster detection tool uses a linear Support Vector Classifier (SVC) to detect man-made and natural disasters, and a density-based spatial clustering of applications with noise (DBSCAN) algorithm to accurately estimate a disaster’s geographic location. This paper provides two original contributions. The first is combining the automated disaster detection tool with the prototype portal for NGO identification. This unique combination could help reduce the time taken to raise awareness of the disaster detected, improve the coordination of aid, increase the amount of aid delivered as a percentage of initial donations and improve aid effectiveness. The second contribution is a general framework that categorises the different approaches that can be adopted for disaster detection. Furthermore, this paper uses responses obtained from an on-the-ground survey with NGOs in the disaster-hit region of Uttar Pradesh, India, to provide actionable insights into how the portal can be developed further.

     

Persistent Random Walks. I. Recurrence Versus Transience

We consider a walker on the line that at each step keeps the same direction with a probability which depends on the time already spent in the direction the walker is currently moving. These walks with memories of variable length can be seen as generalizations of directionally reinforced random walks introduced in Mauldin et al. (Adv Math 117(2):239–252, 1996). We give a complete and usable characterization of the recurrence or transience in terms of the probabilities to switch the direction and we formulate some laws of large numbers. The most fruitful situation emerges when the running times both have an infinite mean. In that case, these properties are related to the behaviour of some embedded random walk with an undefined drift so that these features depend on the asymptotics of the distribution tails related to the persistence times. In the other case, the criterion reduces to a null-drift condition. Finally, we deduce some criteria for a wider class of persistent random walks whose increments are encoded by a variable length Markov chain having—in full generality—no renewal pattern in such a way that their study does not reduce to a skeleton RW as for the original model.