Abstract
Abstract. Increase in access to mobile phone devices and social media networks has changed the way people report and respond to disasters. Community-driven initiatives such as Stand By Task Force (SBTF) or GISCorps have shown great potential by crowdsourcing the acquisition, analysis, and geolocation of social media data for disaster responders. These initiatives face two main challenges: (1) most of social media content such as photos and videos are not geolocated, thus preventing the information to be used by emergency responders, and (2) they lack tools to manage volunteers contributions and aggregate them in order to ensure high quality and reliable results. This paper illustrates the use of a crowdsourcing platform that combines automatic methods for gathering information from social media and crowdsourcing techniques, in order to manage and aggregate volunteers contributions. High precision geolocation is achieved by combining data mining techniques for estimating the location of photos and videos from social media, and crowdsourcing for the validation and/or improvement of the estimated location. The evaluation of the proposed approach is carried out using data related to the Amatrice Earthquake in 2016, coming from Flickr, Twitter and Youtube. A common data set is analyzed and geolocated by both the volunteers using the proposed platform and a group of experts. Data quality and data reliability is assessed by comparing volunteers versus experts results. Final results are shown in a web map service providing a global view of the information social media provided about the Amatrice Earthquake event.
Highlights
The second generation of the world wide web, Web2.0 or the the participatory web, as they call it, has changed the way people time-sensitive tasks and other such micro-tasks
We propose an enrichment of information extracted from social media using crowdsourcing in two directions: (1) increasing the relevance of data by filtering data considered irrelevant by volunteers, and (2) Geolocating each of the relevant social media imagery (Photo & Video)
4.3.1 Expert evaluation First, we analyze the results of the geolocation carried out by the experts, showing the extent to which the selected social media content can be geolocated.Figure 6 shows that 49% of posts have been geolocated with a high precision, i.e., experts claimed to geolocate the social media content with a precision of one point in the map. 10% of the posts were located at the level of the street, road, path or similar. 38% were located at the city level, e.g. a picture was taken in Amatrice, but the experts are not able to geolocate it inside Amatrice
Summary
The second generation of the world wide web, Web2.0 or the the participatory web, as they call it, has changed the way people time-sensitive tasks and other such micro-tasks. People known crowdsourcing communities, who have contributed a have started using the web not just as a source of information, great deal during various disasters. While crowdsourcing is an and as a platform where they share, create and contribute organisational framework and corresponds to processes for pro-. The increase in social media usage curing services from a large amount of people external to an orand the giant leap in the technological advancement has facilit- ganisation, for example communities like SBTF Human based ated the speed, quantity and quality of first hand information at- computation is an information processing framework and cortained from the ground. In 2010, Haiti earthquake showed notation of large sets of images captured during crisis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
